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

    Neuronpedia

    INDEX
    Explanations

    months

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rsa
    -0.07
    bsite
    -0.07
    amentals
    -0.07
     insert
    -0.07
    ㈔
    -0.07
    Technical
    -0.07
    olls
    -0.07
    �
    -0.07
     Scholar
    -0.07
     resume
    -0.07
    POSITIVE LOGITS
    知道自己
    0.07
    гар
    0.07
     remarkably
    0.07
    察觉
    0.07
     unpleasant
    0.07
    ꧊
    0.07
    知名企业
    0.07
    .drawer
    0.07
    شاه
    0.07
     secretly
    0.07
    Act Density 0.009%

    No Known Activations