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

    Neuronpedia

    INDEX
    Explanations

    occurrences of special characters or formatting symbols within the text

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

    numbers and years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Numerade
    -0.51
    səhifə
    -0.50
    tagHelperRunner
    -0.50
     transfieras
    -0.47
     通販
    -0.46
     Италијани
    -0.46
    Ответить
    -0.42
    ፩
    -0.42
    ACHUSET
    -0.42
    RTEE
    -0.42
    POSITIVE LOGITS
    UpInside
    0.41
    #
    0.40
     виправивши
    0.39
    çoivent
    0.38
     avoient
    0.38
     DbSet
    0.38
    expliquer
    0.38
    Referências
    0.36
     Majefty
    0.36
     descans
    0.35
    Act Density 0.230%

    No Known Activations