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

    Neuronpedia

    INDEX
    Explanations

    Emphatic statements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _sibling
    -0.07
    obb
    -0.06
     เ
    -0.06
    Ware
    -0.06
    Firebase
    -0.06
    afc
    -0.06
    ADC
    -0.06
    асс
    -0.06
     범
    -0.06
     tuyệt
    -0.06
    POSITIVE LOGITS
    owitz
    0.07
     fabricated
    0.07
    udem
    0.07
    kinson
    0.06
    kap
    0.06
     egregious
    0.06
     oh
    0.06
    ousse
    0.06
    /update
    0.06
    -Pro
    0.06
    Act Density 0.034%

    No Known Activations