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

    Neuronpedia

    INDEX
    Explanations

    stories when

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.45
    epsilon
    0.44
    your
    0.44
    ੧
    0.44
     تمہ
    0.43
     svjets
    0.43
     Sedangkan
    0.42
    0.41
    ngày
    0.41
    屁
    0.41
    POSITIVE LOGITS
    0.52
     to
    0.51
     hoof
    0.47
     de
    0.46
     et
    0.45
     put
    0.45
     destac
    0.45
     professionals
    0.44
     be
    0.44
     in
    0.44
    Act Density 0.000%

    No Known Activations