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

    Neuronpedia

    INDEX
    Explanations

    recover and its outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     unresolved
    2.83
    ===============
    2.75
    हट
    2.48
     omission
    2.47
    ಙ
    2.41
    coords
    2.41
    2.40
    ifiable
    2.39
     désir
    2.34
     repr
    2.32
    POSITIVE LOGITS
    i
    5.14
    ي
    4.95
    л
    4.45
    ি
    4.24
    e
    4.23
    י
    3.71
     fuese
    3.36
    ი
    3.33
    iiv
    3.24
    o
    3.19
    Act Density 0.008%

    No Known Activations