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

    Neuronpedia

    INDEX
    Explanations

    out

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .win
    -0.07
    ismic
    -0.07
     shoulders
    -0.07
    頃
    -0.07
     روند
    -0.07
    :<
    -0.06
     probes
    -0.06
     başkan
    -0.06
    -filled
    -0.06
     estrogen
    -0.06
    POSITIVE LOGITS
    mant
    0.07
     farklı
    0.06
     fle
    0.06
    ΑΓ
    0.06
    ประส
    0.06
    .RemoveAt
    0.06
    accumulate
    0.06
    .defaultProps
    0.06
     Recommendation
    0.06
    Uses
    0.06
    Act Density 0.003%

    No Known Activations