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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     suffer
    -0.07
    bagai
    -0.07
    esso
    -0.06
    �
    -0.06
    ⎥
    -0.06
     рецепт
    -0.06
    ativos
    -0.06
    izo
    -0.06
    すぎ
    -0.06
    liwości
    -0.06
    POSITIVE LOGITS
    前线
    0.07
    .retry
    0.07
    SUM
    0.07
     Personally
    0.07
     Frankie
    0.07
     Groups
    0.07
    Anti
    0.06
     Sadly
    0.06
     zone
    0.06
    Yeah
    0.06
    Act Density 0.001%

    No Known Activations