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
     Lawyer
    -0.07
    μερ
    -0.07
    兼
    -0.06
    <W
    -0.06
    upd
    -0.06
    590
    -0.06
    .rollback
    -0.06
     چیز
    -0.06
    _CLI
    -0.06
     POLIT
    -0.06
    POSITIVE LOGITS
     foc
    0.06
    　 　 　 　
    0.06
     glyphicon
    0.06
     وجه
    0.06
    ottage
    0.06
    (In
    0.06
     PSP
    0.06
     lange
    0.05
    외
    0.05
     mô
    0.05
    Act Density 0.005%

    No Known Activations