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

    Neuronpedia

    INDEX
    Explanations

    8 within phone numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     safe
    0.69
     inh
    0.68
    safe
    0.62
    சு
    0.60
     Safe
    0.59
    Safe
    0.56
     স্বাভাবিক
    0.56
    sust
    0.54
     thanked
    0.54
    ڑ
    0.53
    POSITIVE LOGITS
     EPL
    0.70
     entidades
    0.66
    ヘッド
    0.66
     okres
    0.66
     періо
    0.66
    acyj
    0.66
    entation
    0.64
    Period
    0.64
     cabeça
    0.63
     gaya
    0.63
    Act Density 0.117%

    No Known Activations