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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    253
    -0.08
    肯
    -0.07
     wouldn
    -0.07
     Shield
    -0.07
     περί
    -0.06
     hasn
    -0.06
    沟
    -0.06
    _cert
    -0.06
     Olympics
    -0.06
    _val
    -0.06
    POSITIVE LOGITS
     strs
    0.07
    /*----------------------------------------------------------------------------
    0.07
     recruitment
    0.06
    Round
    0.06
    Sept
    0.06
    .DESC
    0.06
    .fc
    0.06
     olup
    0.06
    (EIF
    0.06
    لاث
    0.06
    Act Density 0.012%

    No Known Activations