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

    Neuronpedia

    INDEX
    Explanations

    where

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     telefone
    -0.07
    ￩
    -0.07
     replicas
    -0.07
    河流
    -0.07
     Technologies
    -0.07
     Selection
    -0.07
     Lust
    -0.07
     Buffalo
    -0.07
     monumental
    -0.07
    🐅
    -0.07
    POSITIVE LOGITS
    .dat
    0.08
    中介
    0.08
    INTER
    0.07
    顽
    0.07
    相应
    0.07
     ومع
    0.07
    .hot
    0.07
    >>>>>>>>
    0.07
    אונ
    0.07
    <div
    0.07
    Act Density 0.000%

    No Known Activations