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

    Neuronpedia

    INDEX
    Explanations

    Cir

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .shiro
    -0.06
     درآمد
    -0.06
    开放
    -0.06
     челов
    -0.06
    Peak
    -0.06
     вина
    -0.06
     cít
    -0.06
     Holy
    -0.06
    くれる
    -0.06
    .social
    -0.06
    POSITIVE LOGITS
    estate
    0.07
     …↵
    0.07
     –↵↵
    0.07
    >");↵↵
    0.06
    CLASS
    0.06
     )↵↵↵
    0.06
     Furthermore
    0.06
     empower
    0.06
     inspirational
    0.06
     Gear
    0.06
    Act Density 0.001%

    No Known Activations