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

    Neuronpedia

    INDEX
    Explanations

    ign

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     release
    -0.07
    ं
    -0.06
    ớ
    -0.06
     tubes
    -0.06
    ze
    -0.06
    STATUS
    -0.06
    plt
    -0.06
    üçük
    -0.06
     soaking
    -0.06
     yanlış
    -0.06
    POSITIVE LOGITS
    (){}↵
    0.07
    >Type
    0.06
    inda
    0.06
    文
    0.06
    owied
    0.06
     dirname
    0.06
    ')):↵
    0.06
     Origin
    0.06
    turn
    0.06
    -condition
    0.06
    Act Density 0.001%

    No Known Activations