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

    Neuronpedia

    INDEX
    Explanations

    methods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     project
    -0.07
    .NewReader
    -0.07
     Barack
    -0.07
    ιά
    -0.06
    ipment
    -0.06
    —I
    -0.06
    ờ
    -0.06
     integer
    -0.06
    ，没有
    -0.06
    //----------------------------------------------------------------------------
    -0.06
    POSITIVE LOGITS
     행
    0.07
    _REPLACE
    0.06
     κύ
    0.06
    kon
    0.06
     Laser
    0.06
     blunt
    0.06
    рист
    0.06
    орон
    0.06
    ніч
    0.06
    umd
    0.06
    Act Density 0.029%

    No Known Activations