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

    Neuronpedia

    INDEX
    Explanations

    PyTorch DataLoader

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    on
    0.70
    az
    0.56
    ayv
    0.56
    잎
    0.54
    ၷ
    0.54
     않았
    0.53
     విషయం
    0.53
    िंट
    0.52
    cdf
    0.52
    nf
    0.51
    POSITIVE LOGITS
     labyr
    0.50
     потре
    0.49
    ,
    0.48
     incisions
    0.46
     kappa
    0.46
    Levi
    0.45
     ung
    0.45
    டக
    0.45
     invers
    0.44
     mismos
    0.44
    Act Density 0.000%

    No Known Activations