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

    Neuronpedia

    INDEX
    Explanations

    lack of resources

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     guilty
    -0.07
     flagged
    -0.07
    写着
    -0.07
    会不会
    -0.07
    挥发
    -0.07
    荔枝
    -0.07
    .Detail
    -0.07
    了一遍
    -0.07
     Ray
    -0.07
    窬
    -0.07
    POSITIVE LOGITS
    Islamic
    0.07
    formance
    0.07
    /sh
    0.07
    olygon
    0.07
     INIT
    0.06
    oples
    0.06
     ORM
    0.06
    bury
    0.06
    (steps
    0.06
     orm
    0.06
    Act Density 0.066%

    No Known Activations