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

    Neuronpedia

    INDEX
    Explanations

    d

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dps
    -0.07
     waitress
    -0.07
    �
    -0.06
    诹
    -0.06
     Learn
    -0.06
     %(
    -0.06
    Career
    -0.06
    *K
    -0.06
     removeAll
    -0.06
    PRIMARY
    -0.06
    POSITIVE LOGITS
    ص
    0.08
     Friedrich
    0.07
     collected
    0.07
    liwości
    0.07
     состоит
    0.07
    ้อม
    0.07
    bolt
    0.06
     inflated
    0.06
    стан
    0.06
    还要
    0.06
    Act Density 0.000%

    No Known Activations