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

    Neuronpedia

    INDEX
    Explanations

    formal and structured language

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

    Text following colons or quotes

    np_acts-logits-general · gemini-2.0-flash

    structured text or code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pierw
    -0.55
     dinas
    -0.52
    وعة
    -0.51
    txtName
    -0.50
    доби
    -0.49
    Servus
    -0.49
    ImageContext
    -0.49
    InputTagHelper
    -0.48
    DriverManager
    -0.48
    rån
    -0.48
    POSITIVE LOGITS
    Parcelize
    0.75
    ↵↵
    0.72
    }$.\\
    0.63
    ↵↵↵
    0.63
    ).\\
    0.61
    PerformLayout
    0.61
    .\\
    0.61
    $.\\
    0.60
    {}",
    0.58
    .
    0.58
    Act Density 0.037%

    No Known Activations