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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    י
    2.05
    i
    1.81
    ي
    1.77
    ल
    1.76
    서
    1.70
    ی
    1.60
    剂
    1.55
    වර
    1.52
    al
    1.51
    gado
    1.50
    POSITIVE LOGITS
     fierce
    1.66
     propria
    1.56
     mixt
    1.55
    𝟐
    1.54
     fittings
    1.52
     solemnly
    1.51
    𝒆
    1.51
    んばんは
    1.48
     plr
    1.47
     relentless
    1.45
    Act Density 0.000%

    No Known Activations