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

    Neuronpedia

    INDEX
    Explanations

    .youtube

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dent
    -0.07
     Turtle
    -0.07
    ход
    -0.07
     cover
    -0.07
    attrs
    -0.07
    SCORE
    -0.06
    ][:
    -0.06
     Combat
    -0.06
    ServletRequest
    -0.06
    vak
    -0.06
    POSITIVE LOGITS
     имеет
    0.08
    _experiment
    0.08
     ни
    0.07
     explores
    0.07
    ExceptionHandler
    0.07
    �장
    0.07
    inium
    0.06
     injected
    0.06
    ».↵
    0.06
    'll
    0.06
    Act Density 0.014%

    No Known Activations