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

    Neuronpedia

    INDEX
    Explanations

    participant in contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    তল
    2.77
     appealing
    2.72
    hide
    2.57
    𝐠
    2.56
    largest
    2.53
    torch
    2.53
     procedente
    2.52
    memcpy
    2.51
    hwa
    2.48
    ック
    2.45
    POSITIVE LOGITS
    на
    3.13
    ின்
    2.95
    ীদার
    2.84
    м
    2.76
    ше
    2.70
    ル
    2.64
    ן
    2.55
    it
    2.54
    ും
    2.44
    습니다
    2.42
    Act Density 0.017%

    No Known Activations