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

    Neuronpedia

    INDEX
    Explanations

    px

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     eminent
    -0.08
    character
    -0.08
     recover
    -0.07
    recover
    -0.07
    _character
    -0.07
    -derived
    -0.07
    int
    -0.07
     quadratic
    -0.07
     Caracter
    -0.07
     recovered
    -0.07
    POSITIVE LOGITS
    椒
    0.09
     微信
    0.08
     стоит
    0.08
    /min
    0.08
     reacting
    0.08
    专
    0.08
     подойдет
    0.08
     посв
    0.08
    ประ
    0.08
     adaptés
    0.07
    Act Density 0.002%

    No Known Activations