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

    Neuronpedia

    INDEX
    Explanations

    paths and settings related to system configuration or file management

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

    Follows a period or start of turn

    np_acts-logits-general · gemini-2.0-flash

    function and parameter specifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -1.00
    MLLoader
    -0.81
     resourceCulture
    -0.79
    ſicht
    -0.78
    Autoritní
    -0.78
     ſelbſt
    -0.78
    iſche
    -0.78
     estekak
    -0.77
    iſen
    -0.77
    expandindo
    -0.77
    POSITIVE LOGITS
     consideration
    0.32
     stipulation
    0.30
     restrictions
    0.30
     safety
    0.30
     option
    0.30
     options
    0.30
     protection
    0.29
    /
    0.28
    rektur
    0.28
     specified
    0.27
    Act Density 0.315%

    No Known Activations