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

    Neuronpedia

    INDEX
    Explanations

    self

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     HttpSession
    -0.07
    ucus
    -0.06
     Ext
    -0.06
    uture
    -0.06
    判
    -0.06
    clar
    -0.06
     Avery
    -0.06
    سة
    -0.06
    _softmax
    -0.06
    ToFile
    -0.06
    POSITIVE LOGITS
     accidents
    0.07
     mountain
    0.06
     Sonuç
    0.06
    éfono
    0.06
     practitioner
    0.06
     river
    0.06
     joke
    0.06
     ￥
    0.06
     commissions
    0.06
    181
    0.06
    Act Density 0.296%

    No Known Activations