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

    Neuronpedia

    INDEX
    Explanations

    identifiers and data references associated with formatting and updates in documents or code

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

    Code or equations followed by parentheses

    np_acts-logits-general · gemini-2.0-flash

    closing punctuation and code delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مشين
    -0.65
    Vidite
    -0.64
     Moslem
    -0.61
     Latimer
    -0.61
     scolaires
    -0.60
     causation
    -0.59
     plotly
    -0.59
    Azur
    -0.58
     chrétiens
    -0.58
     thorax
    -0.58
    POSITIVE LOGITS
     CreateTagHelper
    0.67
    ).
    0.55
    ):
    0.52
     pinulongan
    0.52
    ">
    0.51
    ément
    0.51
    リエーション
    0.51
    Rightarrow
    0.49
    lito
    0.49
    ').
    0.48
    Act Density 0.488%

    No Known Activations