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

    Neuronpedia

    INDEX
    Explanations

    not kind; built; IBinder

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     to
    0.84
     from
    0.71
     at
    0.64
    ਰ
    0.63
    (
    0.59
    }
    0.59
    n
    0.58
    -
    0.56
     with
    0.55
     also
    0.52
    POSITIVE LOGITS
    𝗝
    0.63
    ギ
    0.59
    𝗥
    0.57
     Гуляць
    0.55
    𝒂
    0.54
    ্ব
    0.53
    Alberto
    0.53
    データを
    0.52
     സാഹചര്യ
    0.52
    ıdır
    0.52
    Act Density 0.000%

    No Known Activations