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

    Neuronpedia

    INDEX
    Explanations

    marketing communications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ტ
    0.52
     onderwerp
    0.51
    酴
    0.51
     செய்வத
    0.49
    䢀
    0.49
    也可
    0.48
    壃
    0.48
    贬
    0.47
    État
    0.47
     പുതു
    0.47
    POSITIVE LOGITS
     that
    0.64
    that
    0.53
    mans
    0.45
    fficient
    0.44
    ibrate
    0.43
    bf
    0.42
     continuity
    0.42
    bibnamefont
    0.42
    ↵↵
    0.41
     That
    0.41
    Act Density 0.002%

    No Known Activations