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

    Neuronpedia

    INDEX
    Explanations

    so what

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    amit
    0.41
    stechnik
    0.40
    すぐに
    0.40
    слен
    0.39
    すぐ
    0.39
     Representations
    0.38
    дит
    0.38
    亣
    0.38
    ্কার
    0.38
    amorph
    0.37
    POSITIVE LOGITS
    ledad
    0.79
    journ
    0.78
     sánh
    0.77
    jour
    0.68
     ソ
    0.63
     much
    0.58
    oner
    0.57
    UTHERN
    0.57
    ething
    0.57
     Со
    0.56
    Act Density 0.038%

    No Known Activations