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

    Neuronpedia

    INDEX
    Explanations

    for loop variable j from low

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hands
    0.38
     fals
    0.38
     ہاتھوں
    0.38
     abusers
    0.37
     znale
    0.36
     toen
    0.36
     hands
    0.35
    マ
    0.35
    lid
    0.35
     precision
    0.35
    POSITIVE LOGITS
    يلات
    0.38
    达到
    0.38
     diatom
    0.38
     Representative
    0.37
    用于
    0.36
    رام
    0.36
     pouce
    0.36
    赛季
    0.36
     தூ
    0.36
     meningkat
    0.36
    Act Density 0.006%

    No Known Activations