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

    Neuronpedia

    INDEX
    Explanations

    political

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cuối
    -0.07
    _Code
    -0.07
    _ComCallableWrapper
    -0.07
     experience
    -0.06
    、大
    -0.06
    licensed
    -0.06
     små
    -0.06
    jian
    -0.06
     phổ
    -0.06
     CRA
    -0.06
    POSITIVE LOGITS
     political
    0.09
    orns
    0.07
     Political
    0.06
     bast
    0.06
    bakan
    0.06
     Freedom
    0.06
     Engl
    0.06
    _ARGUMENT
    0.06
     deadline
    0.06
    stal
    0.06
    Act Density 0.013%

    No Known Activations