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

    Neuronpedia

    INDEX
    Explanations

    her

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     happen
    -0.06
    Все
    -0.06
    ectomy
    -0.06
    Entre
    -0.06
     regard
    -0.06
    bage
    -0.06
    團
    -0.06
    Extras
    -0.06
    �
    -0.06
    William
    -0.06
    POSITIVE LOGITS
    clid
    0.06
    -elect
    0.06
    addtogroup
    0.06
     schwar
    0.06
    /payment
    0.06
     '%'
    0.06
     ceiling
    0.06
    σ
    0.06
     stringstream
    0.06
    .ft
    0.06
    Act Density 0.024%

    No Known Activations