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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    geo
    -0.07
    USD
    -0.07
    椁
    -0.07
    Josh
    -0.07
    ℛ
    -0.07
     FIXED
    -0.07
     Bakery
    -0.06
    𝓕
    -0.06
     Gy
    -0.06
    犏
    -0.06
    POSITIVE LOGITS
    gre
    0.07
    ائها
    0.07
     loại
    0.06
    _sh
    0.06
    _GRE
    0.06
     Leh
    0.06
    _closure
    0.06
    assa
    0.06
     gương
    0.06
    สม
    0.06
    Act Density 0.000%

    No Known Activations