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

    Neuronpedia

    INDEX
    Explanations

    offender

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    噫
    -0.08
     función
    -0.08
    伺
    -0.08
    ems
    -0.07
    /Base
    -0.07
    力求
    -0.07
     najbli
    -0.07
    [block
    -0.07
     grund
    -0.07
    表扬
    -0.07
    POSITIVE LOGITS
    癌
    0.07
     illegally
    0.07
    教学
    0.07
    Ut
    0.07
    _directory
    0.07
    IPA
    0.07
    -covered
    0.07
    ."↵↵
    0.07
    (cp
    0.07
     Rehabilitation
    0.07
    Act Density 0.001%

    No Known Activations