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

    Neuronpedia

    INDEX
    Explanations

    unethical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ixon
    -0.07
    专家
    -0.07
    دول
    -0.07
     dejtings
    -0.07
    跃
    -0.07
    취
    -0.07
    xf
    -0.06
    运动
    -0.06
    xcf
    -0.06
    xe
    -0.06
    POSITIVE LOGITS
     Har
    0.07
    ONY
    0.07
     sauce
    0.07
     أو
    0.06
    🎆
    0.06
     shortages
    0.06
    ниц
    0.06
    }->{
    0.06
    -categories
    0.06
    _args
    0.06
    Act Density 0.007%

    No Known Activations