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

    Neuronpedia

    INDEX
    Explanations

    commands or directives that suggest taking action

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

    "Make" followed by a suggestion

    np_acts-logits-general · gemini-2.0-flash

    make sure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCompany
    -1.09
     itſelf
    -1.00
    DockStyle
    -0.98
     unknownFields
    -0.96
    Personensuche
    -0.94
    AsUp
    -0.88
    tanleria
    -0.88
    Награды
    -0.86
     myſelf
    -0.85
    IBarButtonItem
    -0.84
    POSITIVE LOGITS
     sure
    0.93
     made
    0.76
    makes
    0.73
    make
    0.73
    made
    0.72
    Makes
    0.72
    Make
    0.70
     MAKE
    0.70
    MADE
    0.69
     Makers
    0.68
    Act Density 0.123%

    No Known Activations