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

    Neuronpedia

    INDEX
    Explanations

    code and math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _builtin
    -0.07
    imation
    -0.07
    92
    -0.06
    Unified
    -0.06
     scrolling
    -0.06
    灰
    -0.06
     Ext
    -0.06
    /packages
    -0.06
    esto
    -0.06
    azard
    -0.06
    POSITIVE LOGITS
     abbiamo
    0.07
     αρ
    0.07
     společnost
    0.06
    _WRITE
    0.06
     ул
    0.06
     अन
    0.06
    設
    0.06
    Species
    0.06
     Additional
    0.06
    ，说
    0.06
    Act Density 0.067%

    No Known Activations