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

    Neuronpedia

    INDEX
    Explanations

    tokens with leading whitespace characters or specific formatting

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

    programming code and configuration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    EndContext
    -0.50
     estekak
    -0.49
    __(/*!
    -0.47
    TemporalType
    -0.44
    __]
    -0.42
    HostException
    -0.39
     незавершена
    -0.39
    Билгалдахарш
    -0.38
     protoimpl
    -0.37
    -0.36
    POSITIVE LOGITS
    WebElementEntity
    0.54
     Monfieur
    0.51
     ActionResult
    0.48
     ſte
    0.48
     myſelf
    0.48
     themſelves
    0.47
     Houſe
    0.47
    lingu
    0.47
     IActionResult
    0.46
    curate
    0.46
    Act Density 0.015%

    No Known Activations