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

    Neuronpedia

    INDEX
    Explanations

    abbreviations or initialisms

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     handicrafts
    0.45
     indoctr
    0.44
     childish
    0.43
     neutrinos
    0.43
    𒐪
    0.42
     upbringing
    0.42
     overfitting
    0.42
     figuratively
    0.42
     utensils
    0.41
     propositional
    0.41
    POSITIVE LOGITS
    Past
    0.42
    P
    0.41
    JEN
    0.41
    ANG
    0.40
    Kons
    0.39
    M
    0.39
    O
    0.39
    Ak
    0.38
    Festival
    0.38
    W
    0.38
    Act Density 0.224%

    No Known Activations