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

    Neuronpedia

    INDEX
    Explanations

    image resizing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     méthode
    1.59
    etches
    1.55
     disampaikan
    1.54
    plicity
    1.54
     sheaves
    1.48
    dra
    1.47
    திரு
    1.46
    dessä
    1.44
     méthodes
    1.43
    ilmesi
    1.40
    POSITIVE LOGITS
     Koordin
    2.11
     laut
    2.09
     базо
    2.07
    wide
    2.05
    WIDE
    2.03
     покра
    1.96
     سطح
    1.96
    scapes
    1.93
    客厅
    1.83
    widet
    1.81
    Act Density 0.309%

    No Known Activations