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

    Neuronpedia

    INDEX
    Explanations

    const

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bail
    -0.08
     Pool
    -0.07
    ym
    -0.07
     tert
    -0.07
    cer
    -0.07
     Ug
    -0.06
    YP
    -0.06
    jadi
    -0.06
     spaces
    -0.06
     افراد
    -0.06
    POSITIVE LOGITS
    _succ
    0.07
    .Globalization
    0.07
    _DEFIN
    0.06
    итуа
    0.06
    -finals
    0.06
     advisor
    0.06
    (cos
    0.06
     клу
    0.06
    [::-
    0.06
    plaint
    0.06
    Act Density 0.006%

    No Known Activations