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

    Neuronpedia

    INDEX
    Explanations

    Function Declaration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    內容
    0.52
     내용을
    0.46
     [#
    0.44
    íbrio
    0.43
    蜢
    0.42
     చెప్ప
    0.41
     அடிக்க
    0.41
    content
    0.40
     சென்று
    0.40
    ípios
    0.40
    POSITIVE LOGITS
    ᱵ
    0.39
     substituted
    0.37
    ৃ
    0.37
     trading
    0.37
    Kot
    0.36
    लंका
    0.36
     tabella
    0.36
     reliability
    0.35
    Scientific
    0.35
    accia
    0.35
    Act Density 0.000%

    No Known Activations