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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    🐗
    -0.07
     Hexatrigesimal
    -0.07
     Donetsk
    -0.07
    🎶
    -0.07
    ք
    -0.07
    📚
    -0.07
    🏺
    -0.07
    _CAP
    -0.07
     Yin
    -0.07
    主打
    -0.07
    POSITIVE LOGITS
    abil
    0.07
    imer
    0.07
    alla
    0.07
    _comm
    0.06
    参与
    0.06
    ilities
    0.06
    dic
    0.06
    徐
    0.06
     batch
    0.06
    mem
    0.06
    Act Density 0.044%

    No Known Activations