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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     relate
    -0.06
     Pandora
    -0.06
     event
    -0.06
    /lg
    -0.06
    (cm
    -0.06
     hc
    -0.06
     ^(
    -0.06
     "$
    -0.06
     unde
    -0.06
     Shuttle
    -0.06
    POSITIVE LOGITS
    ους
    0.07
    <!
    0.07
    画像
    0.07
    λοι
    0.07
     antis
    0.07
    .API
    0.06
     advoc
    0.06
    公
    0.06
    .jms
    0.06
    quit
    0.06
    Act Density 0.000%

    No Known Activations