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

    Neuronpedia

    INDEX
    Explanations

    controlled by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    onycha
    1.09
    вил
    1.08
    etière
    1.07
    álen
    1.07
    nál
    1.06
    omata
    1.05
    ⮚
    1.05
    1.03
    د
    1.02
    ложена
    1.02
    POSITIVE LOGITS
    i
    1.55
    in
    1.29
    ↵
    1.25
    t
    1.11
    un
    1.08
    az
    1.06
    an
    1.05
    ge
    1.05
    less
    1.05
     somew
    1.02
    Act Density 0.000%

    No Known Activations