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

    Neuronpedia

    INDEX
    Explanations

    hear about

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    เมนต์
    0.63
     It
    0.61
     Emm
    0.60
     ASUS
    0.60
     Acanth
    0.60
     This
    0.59
     Its
    0.59
     tattoos
    0.59
     Overwatch
    0.59
    oires
    0.59
    POSITIVE LOGITS
     heard
    0.78
     hear
    0.73
    heard
    0.72
    2
    0.71
    5
    0.70
    8
    0.64
     듣
    0.63
    3
    0.62
    Hear
    0.60
    👂
    0.60
    Act Density 0.019%

    No Known Activations