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

    Neuronpedia

    INDEX
    Explanations

    questions or requests for help

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

    I am trying

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    FunctionFlags
    -0.65
    MLLoader
    -0.63
     betweenstory
    -0.57
    ::_('
    -0.50
    SequentialGroup
    -0.50
    dollis
    -0.50
    TestingModule
    -0.50
     виправивши
    -0.48
    +#+
    -0.47
    tinyos
    -0.47
    POSITIVE LOGITS
     saurait
    0.43
     risol
    0.42
     continuará
    0.37
    RTGC
    0.36
    lösung
    0.35
     sebenarnya
    0.34
    樣
    0.34
    Frust
    0.34
     pasará
    0.34
     komentar
    0.34
    Act Density 0.035%

    No Known Activations