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
     alert
    -0.07
    ова
    -0.07
    FUNC
    -0.06
    elsea
    -0.06
     alerted
    -0.06
    immutable
    -0.06
    	al
    -0.06
    ука
    -0.06
    UserProfile
    -0.06
    erra
    -0.06
    POSITIVE LOGITS
     сот
    0.07
    �
    0.06
     Variation
    0.06
     promot
    0.06
     situación
    0.06
     Obtain
    0.06
    чки
    0.06
    ड़
    0.06
    alore
    0.06
     значение
    0.06
    Act Density 0.126%

    No Known Activations