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

    Neuronpedia

    INDEX
    Explanations

    jurisdiction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    LAN
    -0.06
     เต
    -0.06
    .arg
    -0.06
    HV
    -0.06
    (al
    -0.06
     Hồ
    -0.06
    생님
    -0.06
    YLE
    -0.06
    isor
    -0.06
     آثار
    -0.06
    POSITIVE LOGITS
     youngest
    0.07
     发
    0.07
    -art
    0.06
     während
    0.06
    (master
    0.06
    сим
    0.06
    utenant
    0.06
    >());↵
    0.06
    |:
    0.06
    `;↵↵
    0.06
    Act Density 0.003%

    No Known Activations