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

    Neuronpedia

    INDEX
    Explanations

    patterns and structures within code and data representations

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

    Code, math and statistics notation

    np_acts-logits-general · gemini-2.0-flash

    code and mathematical notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    enumi
    -0.49
    Consejo
    -0.48
    pet
    -0.48
     обе
    -0.48
     l
    -0.47
    glut
    -0.47
    _{{\
    -0.45
     PRO
    -0.44
    gro
    -0.44
    SMR
    -0.44
    POSITIVE LOGITS
     ModelExpression
    0.85
    IsMutable
    0.84
    richTextPanel
    0.82
    numerusform
    0.79
     EconPapers
    0.75
    UserScript
    0.74
    InjectAttribute
    0.72
     användas
    0.69
    Демографія
    0.69
     informée
    0.69
    Act Density 0.183%

    No Known Activations