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

    Neuronpedia

    INDEX
    Explanations

    programming-specific keywords and structure

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

    Code, software, or technical language

    np_acts-logits-general · gemini-2.0-flash

    starts with numbers or punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الحره
    -0.59
    [:]
    -0.53
    phinx
    -0.50
     URI
    -0.48
    actionMode
    -0.47
     AppCompatTheme
    -0.47
     <<<<<<<<<<<<<<
    -0.47
    lapsingToolbar
    -0.46
    să
    -0.45
     Signalez
    -0.45
    POSITIVE LOGITS
    ########.
    0.65
    ImageContext
    0.64
     linkovi
    0.62
     regia
    0.61
     виправивши
    0.59
    Espèce
    0.58
     resourceCulture
    0.57
     OMITTED
    0.56
    Cyfeiriadau
    0.54
     estekak
    0.54
    Act Density 0.046%

    No Known Activations