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

    Neuronpedia

    INDEX
    Explanations

    around stars or prompt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    finders
    0.73
    lend
    0.73
    カール
    0.72
    SPs
    0.71
     distinguish
    0.71
     traverse
    0.70
     জের
    0.70
    lad
    0.68
     Шве
    0.68
     ול
    0.67
    POSITIVE LOGITS
    ${
    1.02
    geqslant
    0.88
    AMENTE
    0.85
    (!$
    0.84
    łącznie
    0.79
    }=
    0.78
    ICHIGAN
    0.73
    Kc
    0.73
    ित
    0.71
     comprend
    0.71
    Act Density 0.000%

    No Known Activations