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

    Neuronpedia

    INDEX
    Explanations

    vital signs and honorary guest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    在
    0.77
    '
    0.72
    (
    0.61
    し
    0.59
     in
    0.59
     invertebrates
    0.59
     I
    0.58
     striées
    0.58
    كار
    0.58
    ك
    0.56
    POSITIVE LOGITS
    ﻤ
    0.72
    ON
    0.71
    ﺘ
    0.70
    ﺒ
    0.69
    ム
    0.65
    ன
    0.64
     звуча
    0.64
    ่วง
    0.63
     barrister
    0.61
    ۹
    0.61
    Act Density 0.000%

    No Known Activations