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

    Neuronpedia

    INDEX
    Explanations

    accumulation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    не
    1.38
    ка
    1.33
    ти
    1.29
    ία
    1.21
    у
    1.15
    ви
    1.13
    кому
    1.13
    boldsymbol
    1.12
    ій
    1.12
    MATERIALS
    1.10
    POSITIVE LOGITS
     of
    1.42
    ล
    1.08
     τρόπο
    1.03
     необходи
    1.02
    ac
    1.02
    樍
    1.01
     consolid
    0.99
    0.99
     acumul
    0.95
     של
    0.94
    Act Density 0.000%

    No Known Activations