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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    $update
    -0.08
    incr
    -0.08
    FIN
    -0.07
    _SCENE
    -0.07
    デ
    -0.07
    枰
    -0.07
    户外
    -0.07
    vecs
    -0.07
    東
    -0.06
    贸
    -0.06
    POSITIVE LOGITS
    =l
    0.08
    .Find
    0.07
     שלי
    0.07
     Rodrigo
    0.07
     GetString
    0.07
    \App
    0.07
    "]).
    0.06
     sooner
    0.06
     בזה
    0.06
    될
    0.06
    Act Density 0.005%

    No Known Activations