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

    Neuronpedia

    INDEX
    Explanations

    TS

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    olle
    -0.08
     yesterday
    -0.07
     Beginner
    -0.07
    uevo
    -0.06
    /content
    -0.06
     ：
    -0.06
     outing
    -0.06
    еть
    -0.06
    OMBRE
    -0.06
     irre
    -0.06
    POSITIVE LOGITS
    巷
    0.07
    �
    0.07
    �
    0.07
    category
    0.07
     truck
    0.07
     looming
    0.07
    깰
    0.07
    钻
    0.07
     stacked
    0.07
    IGINAL
    0.07
    Act Density 0.003%

    No Known Activations