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

    Neuronpedia

    INDEX
    Explanations

    weight

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ule
    -0.07
    683
    -0.07
    ีก
    -0.07
     vertically
    -0.06
    üle
    -0.06
    (IR
    -0.06
     případech
    -0.06
    闭
    -0.06
     Azerbai
    -0.06
     NFC
    -0.06
    POSITIVE LOGITS
     pend
    0.07
    복
    0.07
     Destructor
    0.07
    lej
    0.06
     userType
    0.06
     quam
    0.06
     devam
    0.06
    BracketAccess
    0.06
    :::::|
    0.06
    //--
    0.06
    Act Density 0.001%

    No Known Activations