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

    Neuronpedia

    INDEX
    Explanations

    Android dialog button clicks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jugend
    -0.08
    autoreleasepool
    -0.07
     Sutton
    -0.07
     Everest
    -0.07
    ภา
    -0.07
    youtube
    -0.07
    鲼
    -0.07
     ETA
    -0.07
    bben
    -0.07
     sewage
    -0.07
    POSITIVE LOGITS
    chan
    0.07
     realm
    0.07
    .identifier
    0.07
     зак
    0.07
     dw
    0.07
    되었
    0.07
     указ
    0.07
     wym
    0.07
    谓
    0.06
     �
    0.06
    Act Density 0.001%

    No Known Activations