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

    Neuronpedia

    INDEX
    Explanations

    questions that seek clarification or understanding about a subject

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

    how questions and impossibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ."]
    -0.49
    TextWatcher
    -0.41
     Commencez
    -0.40
    \{\\
    -0.40
     Kini
    -0.40
    meteries
    -0.40
    __':
    -0.39
     AssemblyTitle
    -0.39
     cartridge
    -0.39
    .].
    -0.39
    POSITIVE LOGITS
    Impossible
    0.57
    Cómo
    0.51
     Impossible
    0.50
     impossibile
    0.49
     HOW
    0.49
    impossible
    0.49
    How
    0.47
    how
    0.46
    怎么能
    0.45
     How
    0.45
    Act Density 0.020%

    No Known Activations