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

    Neuronpedia

    INDEX
    Explanations

    automatic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ימות
    -0.08
    స్థ
    -0.08
    hangi
    -0.08
     confiar
    -0.08
     نصب
    -0.08
    יים
    -0.08
    felt
    -0.07
    pital
    -0.07
     felt
    -0.07
     lädt
    -0.07
    POSITIVE LOGITS
     способности
    0.09
     wers
    0.08
     версии
    0.08
     connex
    0.08
     rg
    0.08
     asupra
    0.08
     сверх
    0.07
    中华人民共和国
    0.07
    -cap
    0.07
     yaitu
    0.07
    Act Density 0.002%

    No Known Activations