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

    Neuronpedia

    INDEX
    Explanations

    science, technology, and societal fields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     नुकसान
    0.78
    iccation
    0.75
    中止
    0.75
     aim
    0.75
    escens
    0.75
     none
    0.73
     continent
    0.73
    を
    0.72
     boyut
    0.71
     exile
    0.70
    POSITIVE LOGITS
    ological
    1.23
    ographic
    1.07
    ification
    1.03
    ologically
    1.02
    ability
    0.96
    ically
    0.91
    ographical
    0.91
    inology
    0.88
     ڪ
    0.88
    ographically
    0.87
    Act Density 0.280%

    No Known Activations