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

    Neuronpedia

    INDEX
    Explanations

    html input id attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tiny
    0.46
    algorithm
    0.41
    sprites
    0.40
    ?')
    0.40
    irati
    0.40
    uppercase
    0.39
     irrevers
    0.39
    identical
    0.39
     ಸಾಧ್ಯ
    0.39
    developer
    0.38
    POSITIVE LOGITS
     Frank
    0.43
     Later
    0.42
     $_{
    0.39
     valut
    0.39
     Tom
    0.39
     borr
    0.38
     Ngf
    0.37
     کوشش
    0.36
     orche
    0.36
     さん
    0.36
    Act Density 0.002%

    No Known Activations