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

    Neuronpedia

    INDEX
    Explanations

    version numbers and formatting in specifications

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

    Preceding periods in file paths or code

    np_acts-logits-general · gemini-2.0-flash

    version numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.59
     responsibility
    -0.58
    VersionUID
    -0.55
     risk
    -0.55
    routeProvider
    -0.54
    ConstraintMaker
    -0.54
     assume
    -0.51
     reserve
    -0.50
     respon
    -0.49
     assumes
    -0.49
    POSITIVE LOGITS
     TextInputType
    0.59
    Personensuche
    0.55
    ganu
    0.55
     jurors
    0.54
     kaarangay
    0.54
    học
    0.53
     élus
    0.53
    CDCl
    0.52
     ✭✭
    0.52
    Controllo
    0.52
    Act Density 0.210%

    No Known Activations