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

    Neuronpedia

    INDEX
    Explanations

    risk prediction models

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     denn
    -0.07
     Σύ
    -0.06
     сад
    -0.06
    γι
    -0.06
     seamless
    -0.06
    ファ
    -0.06
    opoly
    -0.06
    lob
    -0.06
    同学
    -0.06
     args
    -0.06
    POSITIVE LOGITS
     دلار
    0.07
    Altern
    0.07
     :</
    0.07
     PTSD
    0.06
    İSİ
    0.06
    [maxn
    0.06
     appraisal
    0.06
    _GENERIC
    0.06
    izzare
    0.06
     ApiException
    0.06
    Act Density 0.022%

    No Known Activations