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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ultan
    -0.07
     jeden
    -0.07
    czas
    -0.07
     Що
    -0.06
     án
    -0.06
    ITER
    -0.06
    *angstrom
    -0.06
     disdain
    -0.06
     Various
    -0.06
     detox
    -0.06
    POSITIVE LOGITS
    ua
    0.06
     misled
    0.06
     vendor
    0.06
    _display
    0.06
     ベ
    0.06
     Nội
    0.06
     Lindsey
    0.06
    post
    0.06
    岸
    0.06
     Equip
    0.05
    Act Density 0.044%

    No Known Activations