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

    Neuronpedia

    INDEX
    Explanations

    sense of duty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ו
    0.97
     duties
    0.85
    ิ
    0.84
    0.83
    (
    0.76
     obligations
    0.75
    in
    0.71
    ח
    0.71
    :
    0.70
    ;
    0.70
    POSITIVE LOGITS
    CCl
    0.70
    他
    0.62
    helium
    0.61
    酸
    0.60
    websites
    0.60
    doped
    0.59
    ^{-
    0.59
    ьте
    0.59
    manifolds
    0.59
    Cxx
    0.59
    Act Density 0.002%

    No Known Activations