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

    Neuronpedia

    INDEX
    Explanations

    programming symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :request
    -0.07
    outine
    -0.07
     Inn
    -0.07
    델
    -0.07
    oved
    -0.07
    reno
    -0.07
    Led
    -0.06
    RDD
    -0.06
     Tucson
    -0.06
    Vehicle
    -0.06
    POSITIVE LOGITS
     "()
    0.06
    ών
    0.06
    .ap
    0.06
    CodeAt
    0.06
    "]="
    0.06
     tolua
    0.06
     telemetry
    0.06
    ;
↵
↵
↵
    0.06
     مح
    0.06
    .Factory
    0.05
    Act Density 0.178%

    No Known Activations