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

    Neuronpedia

    INDEX
    Explanations

    Sekt, Pika, Tribe, Delineate, Mophead, Pleurisy, Fantasies, Llama

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ،
    0.27
    ，
    0.22
     obscured
    0.20
     splatter
    0.20
     illogical
    0.20
    ről
    0.20
     splashes
    0.19
     underwear
    0.19
    6
    0.19
     troughs
    0.19
    POSITIVE LOGITS
    i
    0.26
    ك
    0.26
    ia
    0.25
    ра
    0.25
    на
    0.24
    カ
    0.23
    fonso
    0.22
    ナ
    0.22
    티
    0.22
    А
    0.21
    Act Density 0.756%

    No Known Activations