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

    Neuronpedia

    INDEX
    Explanations

    Product descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fleece
    -0.07
    ्व
    -0.06
     kullanıl
    -0.06
     leans
    -0.06
    tip
    -0.06
    ิลล
    -0.06
     플
    -0.06
     lyrics
    -0.06
     Romance
    -0.06
     Cameras
    -0.06
    POSITIVE LOGITS
    _TestCase
    0.06
    omnia
    0.06
    Kent
    0.06
    417
    0.06
    ;i
    0.06
    .You
    0.06
     року
    0.06
    &ZeroWidthSpace
    0.06
    业务
    0.06
     Caroline
    0.05
    Act Density 0.016%

    No Known Activations