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

    Neuronpedia

    INDEX
    Explanations

    occurrences of parentheses and curly braces in code structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    start of turn user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Steuern
    -0.32
     utile
    -0.31
     Füßen
    -0.31
    那是
    -0.29
    taken
    -0.29
    because
    -0.29
     operation
    -0.28
    ReferenceEquals
    -0.28
    ౌ
    -0.28
     complet
    -0.28
    POSITIVE LOGITS
    transQ
    0.68
     незавершена
    0.56
    Дерекк
    0.55
    \{\\
    0.54
    tvguidetime
    0.53
    enumii
    0.53
     nakalista
    0.53
    脚注の使い方
    0.52
     שוליים
    0.52
    ſelves
    0.51
    Act Density 0.010%

    No Known Activations