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

    Neuronpedia

    INDEX
    Explanations

    github repository paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     alamu
    0.39
    However
    0.39
     ornamentation
    0.39
    ظ
    0.39
     одним
    0.38
     humedad
    0.38
     alerg
    0.38
     alegre
    0.38
     estremamente
    0.37
    vykor
    0.36
    POSITIVE LOGITS
    src
    0.41
    يلي
    0.40
    代码
    0.37
    的代码
    0.37
     ২০১০
    0.35
     ውስጥ
    0.34
    ẹt
    0.34
     './
    0.34
    စီ
    0.34
     Labs
    0.33
    Act Density 0.001%

    No Known Activations