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

    Neuronpedia

    INDEX
    Explanations

    words starting with dv

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    schutz
    0.45
    lé
    0.41
     受け
    0.39
    ◔
    0.38
    മേ
    0.37
    데
    0.37
     हृदय
    0.36
    蜴
    0.36
    繊維
    0.36
    OURCES
    0.35
    POSITIVE LOGITS
     dv
    0.94
     dw
    0.92
     DV
    0.78
     Dw
    0.73
    dw
    0.72
     Dv
    0.71
    dv
    0.68
    DV
    0.68
    Dv
    0.67
    Dw
    0.66
    Act Density 0.002%

    No Known Activations