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

    Neuronpedia

    INDEX
    Explanations

    security deposit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     severed
    0.51
    ಾಗಿ
    0.49
    सामान्यीकृत
    0.49
    лд
    0.48
    もら
    0.48
     Комп
    0.47
    )
    0.47
    >"
    0.47
    Ƹ
    0.47
    "
    0.46
    POSITIVE LOGITS
     utens
    0.56
    m
    0.56
     recipiente
    0.54
     Gost
    0.53
     ہُ
    0.52
     Virg
    0.51
     intestin
    0.51
     teško
    0.50
     rétr
    0.50
     Paston
    0.50
    Act Density 0.003%

    No Known Activations