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

    Neuronpedia

    INDEX
    Explanations

    dialogue, inner monologues

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     や
    -0.07
     <=>
    -0.07
    (Op
    -0.07
     ／
    -0.07
    mtree
    -0.06
    ');</
    -0.06
     Най
    -0.06
     enviado
    -0.06
     چیز
    -0.06
     Ihre
    -0.06
    POSITIVE LOGITS
     smoothing
    0.07
    Implement
    0.06
    ATED
    0.06
    �
    0.06
    ابت
    0.06
     regular
    0.06
     osc
    0.06
    ا
    0.06
    pending
    0.06
    tracted
    0.06
    Act Density 0.261%

    No Known Activations