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

    Neuronpedia

    INDEX
    Explanations

    http:// or web links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.54
     В
    0.48
     be
    0.44
    يل
    0.43
     в
    0.42
     profesora
    0.42
     passiert
    0.42
     medzi
    0.41
     Ф
    0.40
    ర్‌
    0.40
    POSITIVE LOGITS
    ed
    0.65
    c
    0.54
    ות
    0.52
    u
    0.51
    त
    0.50
    ת
    0.48
    на
    0.48
    R
    0.48
    合せ
    0.47
     Set
    0.47
    Act Density 0.000%

    No Known Activations