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

    Neuronpedia

    INDEX
    Explanations

    narrative and developmental processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aleph
    0.52
     квадра
    0.49
    宽度
    0.49
     widths
    0.47
     حقیقت
    0.45
    Width
    0.45
    yj
    0.45
     дату
    0.45
     солнца
    0.44
     width
    0.44
    POSITIVE LOGITS
    flow
    0.46
    bird
    0.44
    ;
    0.43
     slowed
    0.42
     returned
    0.42
     Lambert
    0.42
     CII
    0.42
    xSpeed
    0.42
    р
    0.42
     rain
    0.41
    Act Density 0.000%

    No Known Activations