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

    Neuronpedia

    INDEX
    Explanations

    Code and math formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     faker
    -0.07
     Garr
    -0.07
    .dd
    -0.06
    Tick
    -0.06
    arrera
    -0.06
    collector
    -0.06
    公式
    -0.06
    Scr
    -0.06
     هناك
    -0.06
     противоп
    -0.06
    POSITIVE LOGITS
    filt
    0.07
    pell
    0.06
    stice
    0.06
     volunteer
    0.06
    dbh
    0.06
    ْم
    0.06
     faculties
    0.06
    .Generated
    0.06
    erde
    0.06
    Firestore
    0.06
    Act Density 0.000%

    No Known Activations