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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     explicitly
    -0.07
     freedom
    -0.07
    ываем
    -0.07
    Mem
    -0.07
     addressed
    -0.06
    营商
    -0.06
    AFP
    -0.06
    ística
    -0.06
    מלח
    -0.06
    _DESC
    -0.06
    POSITIVE LOGITS
    江北
    0.07
    /con
    0.07
    eye
    0.06
     وهناك
    0.06
    -taking
    0.06
    𝑄
    0.06
    库
    0.06
    塬
    0.06
    成型
    0.06
    entifier
    0.06
    Act Density 0.047%

    No Known Activations