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

    Neuronpedia

    INDEX
    Explanations

    numbers for helplines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     doubly
    0.67
     thematic
    0.66
     multiplies
    0.62
    asures
    0.62
    odesmium
    0.62
    lasm
    0.62
     constants
    0.61
    dismiss
    0.61
    өк
    0.60
     dyst
    0.60
    POSITIVE LOGITS
     Hearing
    1.10
    Hearing
    1.04
     hearing
    1.00
     heard
    0.93
     Hear
    0.91
    heard
    0.91
    Hear
    0.91
     hear
    0.90
     слы
    0.88
    hearing
    0.86
    Act Density 0.105%

    No Known Activations