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

    Neuronpedia

    INDEX
    Explanations

    phrases separated by periods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ের
    0.42
    },\
    0.42
    一緒に
    0.40
    Dc
    0.40
    _
    0.39
    s
    0.39
    ̣n
    0.38
    ’
    0.38
    otor
    0.38
     outsiders
    0.38
    POSITIVE LOGITS
     страда
    0.49
    abody
    0.49
     Markle
    0.48
     Wilt
    0.47
     पड़ेगी
    0.47
     stair
    0.46
    ॉर्क
    0.45
     sufrir
    0.45
    fade
    0.44
     NODE
    0.44
    Act Density 0.112%

    No Known Activations