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

    Neuronpedia

    INDEX
    Explanations

    The

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     پرد
    -0.07
    他
    -0.07
     threats
    -0.06
    Detection
    -0.06
    emaakt
    -0.06
     mit
    -0.06
    자는
    -0.06
    Quit
    -0.06
     Poverty
    -0.06
     election
    -0.06
    POSITIVE LOGITS
    .↵↵↵↵↵↵↵↵↵↵↵↵
    0.07
    ticker
    0.07
     baktı
    0.07
    .shop
    0.07
     zástup
    0.07
     Král
    0.06
     gezocht
    0.06
     Shopify
    0.06
     ):↵↵
    0.06
    '>↵↵
    0.06
    Act Density 0.139%

    No Known Activations