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

    Neuronpedia

    INDEX
    Explanations

    game

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     eponymous
    0.55
     for
    0.54
    для
    0.53
     opsi
    0.52
     elucidation
    0.51
     a
    0.50
     the
    0.50
     extravaganza
    0.49
     voila
    0.48
     pdf
    0.48
    POSITIVE LOGITS
    󰀄
    0.48
    த்தின்
    0.47
     pueda
    0.46
     विकिरण
    0.46
    的光
    0.46
    滉
    0.46
    뀜
    0.45
    ត្រូវបាន
    0.44
     피부
    0.43
     充電
    0.43
    Act Density 2.313%

    No Known Activations