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

    Neuronpedia

    INDEX
    Explanations

    generating, processing, or comparative

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ｒ
    0.54
    कर्ताओं
    0.50
    ল্প
    0.48
     conectado
    0.44
    AT
    0.44
     Melihat
    0.44
    ﾏ
    0.44
    ειας
    0.44
    foregroundView
    0.44
    łos
    0.43
    POSITIVE LOGITS
     ().
    0.54
     sedative
    0.50
    Y
    0.50
    :
    0.49
     specified
    0.49
     ⭐
    0.47
     (),
    0.46
     infinite
    0.46
    á
    0.46
    of
    0.45
    Act Density 0.000%

    No Known Activations