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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
     RU
    -0.07
    уди
    -0.07
    _BLOCKS
    -0.06
    hud
    -0.06
    }());↵
    -0.06
     teil
    -0.06
     crackers
    -0.06
     slows
    -0.06
    разд
    -0.06
    POSITIVE LOGITS
    Canadian
    0.07
    =color
    0.07
     plunder
    0.06
    ols
    0.06
     imz
    0.06
    “For
    0.06
    setAttribute
    0.06
     Demand
    0.06
    (","
    0.06
    BV
    0.06
    Act Density 0.000%

    No Known Activations