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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    stm
    -0.07
     pare
    -0.07
     ast
    -0.07
    иш
    -0.07
    罕见
    -0.07
    เต
    -0.06
    ред
    -0.06
     אמר
    -0.06
    れて
    -0.06
    ().↵
    -0.06
    POSITIVE LOGITS
    שואה
    0.07
    noopener
    0.06
    Init
    0.06
    ゼ
    0.06
     infinit
    0.06
     Địa
    0.06
    無し�
    0.06
     Helena
    0.06
    _calc
    0.06
    ✃
    0.06
    Act Density 0.002%

    No Known Activations