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

    Neuronpedia

    INDEX
    Explanations

    refers to echo busy completion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     innovative
    0.46
    the
    0.44
     défense
    0.44
     rejuvenating
    0.44
     nabí
    0.44
     illustrious
    0.42
     ún
    0.42
     cocon
    0.42
     đẳng
    0.42
     quantos
    0.42
    POSITIVE LOGITS
    ｼ
    0.48
    7
    0.45
    க்
    0.44
    Trump
    0.44
    Operand
    0.42
     لگانا
    0.42
    (
    0.42
    श
    0.42
    Smo
    0.42
    드의
    0.41
    Act Density 0.002%

    No Known Activations