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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     obligations
    -0.07
    ิง
    -0.07
    Separ
    -0.07
    ٱ
    -0.07
     fin
    -0.07
    שות
    -0.07
    емся
    -0.07
     experiments
    -0.07
     Args
    -0.06
    Ι
    -0.06
    POSITIVE LOGITS
    居委会
    0.08
    ᒼ
    0.07
    /accounts
    0.07
    umno
    0.07
     Panasonic
    0.07
    ڧ
    0.07
    ffc
    0.07
     "(
    0.07
     WK
    0.07
     ابو
    0.06
    Act Density 0.021%

    No Known Activations