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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    position
    -0.07
     Gets
    -0.07
    positions
    -0.07
     Heat
    -0.07
    production
    -0.07
     expands
    -0.06
     Pic
    -0.06
     стандарт
    -0.06
    (condition
    -0.06
     Bol
    -0.06
    POSITIVE LOGITS
     pcm
    0.07
     forfe
    0.07
    ैग
    0.07
     doub
    0.06
     orchest
    0.06
    istor
    0.06
    inally
    0.06
    σμα
    0.06
     UserID
    0.06
     ㅇ
    0.06
    Act Density 0.087%

    No Known Activations