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

    Neuronpedia

    INDEX
    Explanations

    temporary variable in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ットン
    0.40
    ORUS
    0.39
     Loretta
    0.39
    Acetyl
    0.38
    িনায়ক
    0.38
    🧂
    0.37
    サラダ
    0.37
    櫸
    0.37
     вікі
    0.37
    荸
    0.36
    POSITIVE LOGITS
     used
    0.42
     total
    0.39
     s
    0.39
     o
    0.38
     f
    0.38
    r
    0.38
     set
    0.38
     os
    0.38
    else
    0.37
     fast
    0.37
    Act Density 0.001%

    No Known Activations