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

    Neuronpedia

    INDEX
    Explanations

    numerical values with decimal points

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

    numbers like IP addresses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LookAnd
    -0.41
     construct
    -0.41
    ousand
    -0.40
    construct
    -0.39
     Eternal
    -0.39
    anneer
    -0.38
    achery
    -0.35
     Sorrow
    -0.35
     göm
    -0.35
    maine
    -0.35
    POSITIVE LOGITS
    +#+#
    0.70
    脚注の使い方
    0.65
    rungsseite
    0.52
    Personendaten
    0.50
    enumii
    0.49
    MigrationBuilder
    0.48
    0.47
     opérés
    0.47
     Infórmanos
    0.46
    InjectAttribute
    0.46
    Act Density 0.411%

    No Known Activations