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

    Neuronpedia

    INDEX
    Explanations

    The

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ва
    -0.07
     worship
    -0.06
    (wp
    -0.06
     getPage
    -0.06
    setVisibility
    -0.06
     мер
    -0.06
     records
    -0.06
     shake
    -0.06
    jective
    -0.06
    getLast
    -0.06
    POSITIVE LOGITS
    然而
    0.06
    anggan
    0.06
    strftime
    0.06
    法国
    0.06
    *******
↵
    0.06
    REFER
    0.06
    URRED
    0.06
     tslib
    0.06
    _DER
    0.06
    GF
    0.06
    Act Density 0.017%

    No Known Activations