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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     اين
    -0.07
     forfeiture
    -0.07
     čá
    -0.07
    _VC
    -0.07
    lik
    -0.07
    .title
    -0.07
     staveb
    -0.07
    title
    -0.07
    LIK
    -0.07
     konu
    -0.06
    POSITIVE LOGITS
     Excellent
    0.08
     continually
    0.08
    аними
    0.08
    Excellent
    0.08
    asant
    0.06
    .redis
    0.06
     continuously
    0.06
    ipy
    0.06
     constantly
    0.06
    .detail
    0.06
    Act Density 0.014%

    No Known Activations