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

    Neuronpedia

    INDEX
    Explanations

    following A/B

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ogrod
    0.33
     emoticon
    0.32
     extraneous
    0.32
    ográf
    0.32
     objectionable
    0.32
    ાઇલ
    0.31
    زمانہ
    0.31
     foss
    0.31
     گے۔
    0.31
     obl
    0.30
    POSITIVE LOGITS
    was
    0.53
    2
    0.50
     A
    0.49
    Ａ
    0.49
     was
    0.46
    一
    0.46
    than
    0.44
    A
    0.44
    ric
    0.43
    sembly
    0.41
    Act Density 0.098%

    No Known Activations