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

    Neuronpedia

    INDEX
    Explanations

    jalapeños

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tuttavia
    0.69
     Π
    0.64
    も含
    0.63
     Αν
    0.62
     Фонбет
    0.61
     Κ
    0.59
    SelfPermission
    0.59
    кість
    0.58
    қты
    0.58
    Κ
    0.58
    POSITIVE LOGITS
    ”
    0.79
    on
    0.73
    "
    0.63
     scotch
    0.53
     mög
    0.50
    捲
    0.50
    et
    0.50
     einf
    0.50
    onet
    0.50
     aspen
    0.50
    Act Density 0.001%

    No Known Activations