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

    Neuronpedia

    INDEX
    Explanations

    expressions of inability or negation

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

    "Can't" or "cannot" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    cannot + verb of strong feeling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -0.64
     Majefty
    -0.57
     bedoeld
    -0.56
     planas
    -0.56
     auroit
    -0.52
    SUCCEEDED
    -0.52
     communautaire
    -0.51
     <<<<<<<<<<<<<<
    -0.51
    brainly
    -0.50
    onAttach
    -0.50
    POSITIVE LOGITS
     afford
    0.73
    parsedMessage
    0.72
     fathom
    0.71
     imagine
    0.69
     تضيفلها
    0.66
     للاسماء
    0.64
    parseDouble
    0.63
     speak
    0.62
     AspNetCore
    0.59
     figure
    0.58
    Act Density 0.155%

    No Known Activations