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

    Neuronpedia

    INDEX
    Explanations

    WHO

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vend
    -0.07
     Lak
    -0.07
     рань
    -0.06
     Sand
    -0.06
     ка
    -0.06
     Crest
    -0.06
     Floral
    -0.06
    iesen
    -0.06
     Portugal
    -0.06
    agner
    -0.06
    POSITIVE LOGITS
    0.07
    _through
    0.07
    WHO
    0.07
    lluminate
    0.07
    .sec
    0.07
     CHO
    0.07
    ilio
    0.07
    tru
    0.07
     الخط
    0.07
     WHO
    0.06
    Act Density 0.003%

    No Known Activations