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

    Neuronpedia

    INDEX
    Explanations

    Fortunate/Unfortunate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     naked
    -0.06
     SUS
    -0.06
     Forgot
    -0.06
    (extra
    -0.06
     devil
    -0.06
    たり
    -0.06
    のが
    -0.06
     كيف
    -0.06
    겠
    -0.06
    規
    -0.06
    POSITIVE LOGITS
     unfortunate
    0.08
    emachine
    0.07
     documented
    0.07
    Ms
    0.07
     dzie
    0.06
    owych
    0.06
     psychotic
    0.06
    afx
    0.06
    .DateTime
    0.06
    :class
    0.06
    Act Density 0.003%

    No Known Activations