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

    Neuronpedia

    INDEX
    Explanations

    code and non-English text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ice
    -0.06
     Krank
    -0.06
     wooden
    -0.06
     rabbit
    -0.06
    Everyone
    -0.06
    likleri
    -0.06
     cruel
    -0.06
     Harley
    -0.06
    libc
    -0.06
     wk
    -0.06
    POSITIVE LOGITS
    ÷
    0.07
    /N
    0.06
    .:.:.:
    0.06
    рі
    0.06
     버
    0.06
     Erotische
    0.06
    insurance
    0.06
    TAB
    0.06
    [strlen
    0.06
    _refer
    0.06
    Act Density 0.040%

    No Known Activations