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

    Neuronpedia

    INDEX
    Explanations

    say "ry" ending

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     caracteres
    -0.06
    TRUE
    -0.06
    дами
    -0.06
     scala
    -0.06
    abbo
    -0.06
     pouvez
    -0.06
     下午
    -0.06
     typename
    -0.06
    場合は
    -0.06
    .flink
    -0.06
    POSITIVE LOGITS
     IRC
    0.07
     \↵↵
    0.07
     Qué
    0.07
     вт
    0.07
    iff
    0.06
     Highlight
    0.06
    破
    0.06
     ưu
    0.06
     кри
    0.06
    γρά
    0.06
    Act Density 0.003%

    No Known Activations