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

    Neuronpedia

    INDEX
    Explanations

    Non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /ubuntu
    -0.08
    捂
    -0.07
    kus
    -0.07
    best
    -0.07
    _dev
    -0.07
    incare
    -0.07
    	cpu
    -0.07
     seul
    -0.07
    䗖
    -0.07
    Io
    -0.07
    POSITIVE LOGITS
    さまざ
    0.07
    Xã
    0.07
    ˯
    0.06
    心境
    0.06
     النوع
    0.06
     שינוי
    0.06
     ilişki
    0.06
     Bayesian
    0.06
    .Size
    0.06
    0.06
    Act Density 0.008%

    No Known Activations