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

    Neuronpedia

    INDEX
    Explanations

    ID and nonce values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    on
    0.57
    она
    0.52
     এতটা
    0.52
    يس
    0.50
    an
    0.49
    ø
    0.48
    ra
    0.47
    onka
    0.47
     Здесь
    0.46
    р
    0.46
    POSITIVE LOGITS
    HAI
    0.53
    ᓛ
    0.52
     httpServer
    0.51
     серии
    0.49
     Jahres
    0.48
    UAL
    0.48
     synagogues
    0.48
     ſt
    0.48
     यूपी
    0.47
     ތ
    0.47
    Act Density 0.005%

    No Known Activations