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

    Neuronpedia

    INDEX
    Explanations

    understand how

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Technologien
    0.51
     technologies
    0.46
     staples
    0.45
     utens
    0.44
    機能を
    0.44
     उपयोग
    0.43
     ಹಲ
    0.42
     тази
    0.42
     استخدام
    0.42
     doctrines
    0.41
    POSITIVE LOGITS
    urri
    0.46
    ificare
    0.45
    abort
    0.44
    0.44
    ul
    0.43
    gz
    0.43
    ającym
    0.42
    dark
    0.42
    pregnant
    0.42
    concerned
    0.41
    Act Density 0.003%

    No Known Activations