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

    Neuronpedia

    INDEX
    Explanations

    assignment after result

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    City
    0.73
    Ell
    0.68
    是个
    0.64
    是一个
    0.64
    Ag
    0.63
    England
    0.62
    Arg
    0.62
    Alt
    0.60
    Ch
    0.59
    是一個
    0.59
    POSITIVE LOGITS
     translocation
    0.62
     animé
    0.58
     scipy
    0.57
     lingue
    0.55
     pero
    0.55
     compute
    0.55
     musculaire
    0.54
     cognitiva
    0.54
     transcoding
    0.53
     paru
    0.53
    Act Density 0.001%

    No Known Activations