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

    Neuronpedia

    INDEX
    Explanations

    foreign languages and misogyny

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.08
     feu
    -0.07
    ,line
    -0.07
    enan
    -0.07
    ADER
    -0.07
    แ
    -0.07
    /game
    -0.07
     nghiệm
    -0.07
     matte
    -0.07
    大涨
    -0.07
    POSITIVE LOGITS
     Islamabad
    0.07
    .esp
    0.07
    -----------
    0.07
    �
    0.07
    _presence
    0.07
     Mitar
    0.07
     "}↵
    0.07
     titular
    0.07
    FIT
    0.06
    工
    0.06
    Act Density 0.108%

    No Known Activations