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

    Neuronpedia

    INDEX
    Explanations

    pro

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    厅
    -0.07
    _imp
    -0.06
    UTO
    -0.06
     말
    -0.06
     університ
    -0.06
    /API
    -0.06
     tuo
    -0.06
    _FIX
    -0.06
    REAT
    -0.06
     diferencia
    -0.06
    POSITIVE LOGITS
     pro
    0.09
    $
    0.07
    '',
    0.06
    主
    0.06
     Proposal
    0.06
     psychology
    0.06
     request
    0.06
     JSONObject
    0.06
     coordin
    0.06
     ked
    0.06
    Act Density 0.006%

    No Known Activations