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

    Neuronpedia

    INDEX
    Explanations

    personal importance, advice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    廊
    -0.07
    -ons
    -0.07
     otras
    -0.06
    ider
    -0.06
    wa
    -0.06
     ноги
    -0.06
    ificio
    -0.06
     chunk
    -0.06
    aler
    -0.06
     را
    -0.06
    POSITIVE LOGITS
    (features
    0.07
    Simple
    0.06
    )','
    0.06
     electroly
    0.06
    (done
    0.06
     Equity
    0.06
     innov
    0.06
     ssid
    0.06
    (letter
    0.06
    (cols
    0.06
    Act Density 0.041%

    No Known Activations