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

    Neuronpedia

    INDEX
    Explanations

    formal language and specific nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ÇÕES
    1.03
    IRONMENT
    0.99
     workflows
    0.97
     Fähigkeiten
    0.96
     déplacement
    0.95
    tional
    0.95
    ÇÃO
    0.93
    ទំនាក់ទំនង
    0.92
    THERS
    0.92
    赟
    0.92
    POSITIVE LOGITS
    i
    1.03
    u
    0.91
    ~
    0.90
    {
    0.86
    -|
    0.83
    1
    0.83
    ie
    0.81
    ^
    0.80
    j
    0.80
    <
    0.79
    Act Density 0.065%

    No Known Activations