Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    technical terms related to software development and programming concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows "Message" and variable declarations

    np_acts-logits-general · gemini-2.0-flash

    programming identifiers and code definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PerformLayout
    -0.47
    ग्री
    -0.44
    args
    -0.41
     शामिल
    -0.41
    <()>
    -0.40
    ToBe
    -0.40
    segundo
    -0.39
    new
    -0.39
    Second
    -0.39
    Previously
    -0.39
    POSITIVE LOGITS
     getter
    1.03
     ModelExpression
    0.83
     Getter
    0.82
     getters
    0.82
    thenReturn
    0.78
    featureID
    0.77
    IntoConstraints
    0.71
    stateProvider
    0.70
    getter
    0.69
    ]")]
    0.69
    Act Density 0.120%

    No Known Activations