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

    Neuronpedia

    INDEX
    Explanations

    exponents of, high smoke, light touch

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    amic
    0.42
    Tempor
    0.42
    bes
    0.42
    ubes
    0.42
    Add
    0.41
    variants
    0.40
    Friendly
    0.39
    nic
    0.39
    NB
    0.39
    respectively
    0.38
    POSITIVE LOGITS
     interruptions
    0.46
     graphique
    0.45
     Ceremon
    0.44
     ceremon
    0.42
     tracer
    0.42
     ceremonial
    0.42
     punctuated
    0.41
     breakage
    0.41
    EDEN
    0.41
     Ceremony
    0.41
    Act Density 0.002%

    No Known Activations