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

    Neuronpedia

    INDEX
    Explanations

    one followed by a word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    نق
    0.38
    াপিত
    0.38
    othermic
    0.38
     fixer
    0.36
    Trajectories
    0.36
    <_
    0.36
     didactic
    0.36
    ANSI
    0.35
    ｷ
    0.35
    FANG
    0.35
    POSITIVE LOGITS
     One
    0.95
    ToOne
    0.89
    One
    0.84
     Hundred
    0.80
     Thousand
    0.64
    ONE
    0.61
     million
    0.60
     ONE
    0.59
    Hundred
    0.59
     hundred
    0.58
    Act Density 0.010%

    No Known Activations