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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     ConnectionState
    -0.07
    _interrupt
    -0.07
     Congressional
    -0.06
    ило
    -0.06
    社会组织
    -0.06
    下一步
    -0.06
     Neuro
    -0.06
     desarrollo
    -0.06
    几步
    -0.06
    閱
    -0.06
    POSITIVE LOGITS
     PROCESS
    0.08
    Inicial
    0.07
     maiden
    0.07
    iced
    0.07
     Pu
    0.06
    秤
    0.06
     Yo
    0.06
    _likes
    0.06
    äd
    0.06
    帐
    0.06
    Act Density 0.001%

    No Known Activations