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

    Neuronpedia

    INDEX
    Explanations

    know if

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ちゃっ
    0.39
     acerca
    0.39
     információ
    0.38
     begann
    0.37
     aerosol
    0.36
    Tocco
    0.36
     लहान
    0.36
     जिज्ञासा
    0.36
     began
    0.35
     విష
    0.35
    POSITIVE LOGITS
    いつでも
    0.38
    如果你
    0.37
     anytime
    0.37
     ಬೇ
    0.36
     via
    0.36
     sollten
    0.35
    湧
    0.35
     myriad
    0.34
    ለያ
    0.34
    ∖
    0.34
    Act Density 0.009%

    No Known Activations