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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and specific nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    0.91
     I
    0.72
     avoir
    0.72
     O
    0.70
     A
    0.67
     M
    0.65
     automatically
    0.64
     espèce
    0.64
     obligated
    0.64
     eternal
    0.63
    POSITIVE LOGITS
    r
    0.76
    с
    0.61
    t
    0.60
    p
    0.60
    india
    0.58
    0.58
    staking
    0.57
    mil
    0.56
    uk
    0.55
    ّر
    0.55
    Act Density 0.000%

    No Known Activations