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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jogo
    -0.07
     insulated
    -0.06
     peninsula
    -0.06
    (change
    -0.06
     facilitated
    -0.06
     dikke
    -0.06
     zkou
    -0.06
     birinin
    -0.06
     birlik
    -0.06
    出的
    -0.06
    POSITIVE LOGITS
    urent
    0.06
    elihood
    0.06
    pez
    0.06
    _Syntax
    0.06
     strangers
    0.06
     revoke
    0.06
     cats
    0.06
    nav
    0.06
    )}>↵
    0.06
    Emer
    0.06
    Act Density 0.098%

    No Known Activations