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

    Neuronpedia

    INDEX
    Explanations

    russian pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    -alpha
    -0.07
    .cs
    -0.07
     pop
    -0.07
    Ан
    -0.07
    _EDITOR
    -0.06
    Chess
    -0.06
    _partner
    -0.06
     Polo
    -0.06
    (P
    -0.06
    POSITIVE LOGITS
     مبار
    0.07
     즐
    0.07
     reconcile
    0.06
     technique
    0.06
    ChangedEventArgs
    0.06
    )."
    0.06
     ط
    0.06
     novo
    0.06
     viewWillAppear
    0.06
    슈
    0.06
    Act Density 0.010%

    No Known Activations