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

    Neuronpedia

    INDEX
    Explanations

    findings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     아버지
    -0.07
    ICC
    -0.07
    vec
    -0.07
    scope
    -0.07
     encodeURIComponent
    -0.06
    .argument
    -0.06
     tiener
    -0.06
    ：「
    -0.06
    =res
    -0.06
    _rem
    -0.06
    POSITIVE LOGITS
     findings
    0.11
     withholding
    0.08
     sellers
    0.08
     finding
    0.08
     guidelines
    0.07
     Byrne
    0.07
     Flyers
    0.07
     Jets
    0.07
    ुख
    0.06
     Lawn
    0.06
    Act Density 0.012%

    No Known Activations