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

    Neuronpedia

    INDEX
    Explanations

    ?

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ربع
    -0.07
     lowes
    -0.07
    ladesh
    -0.07
    ollywood
    -0.06
     frm
    -0.06
     Lud
    -0.06
     fatt
    -0.06
     Sanford
    -0.06
     Lal
    -0.06
     info
    -0.06
    POSITIVE LOGITS
    ъек
    0.07
    を見る
    0.07
    ($.
    0.06
    _decision
    0.06
     frauen
    0.06
    \data
    0.06
    Gener
    0.06
    .insert
    0.06
     наві
    0.06
    entions
    0.06
    Act Density 0.188%

    No Known Activations