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

    Neuronpedia

    INDEX
    Explanations

    ility

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dfa
    -0.07
     존
    -0.06
     Kw
    -0.06
    _TERM
    -0.06
    _videos
    -0.06
     blasting
    -0.06
    基地
    -0.06
     χρήση
    -0.06
    caption
    -0.06
     ################################################################
    -0.06
    POSITIVE LOGITS
     Lawyer
    0.07
    by
    0.06
     newcomer
    0.06
    _parallel
    0.06
    .responseText
    0.06
    ibile
    0.06
     lombok
    0.06
    ull
    0.06
    .dto
    0.06
    airy
    0.06
    Act Density 0.006%

    No Known Activations