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

    Neuronpedia

    INDEX
    Explanations

    pretty simple concept

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .}
    0.59
    .",
    0.51
    .'”
    0.50
    ."""
    0.49
    atthaya
    0.49
     epiphany
    0.48
    }.
    0.48
    .',
    0.48
    .'''
    0.47
    ội
    0.47
    POSITIVE LOGITS
    ال
    0.52
    Agr
    0.48
    في
    0.46
    \
    0.45
    ন
    0.45
     charg
    0.43
    رب
    0.41
    دون
    0.41
    िक
    0.41
     dich
    0.40
    Act Density 0.003%

    No Known Activations