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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to measurements or specifications

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

    numbers and versions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    expandindo
    -0.81
    SharedDtor
    -0.70
    tanleria
    -0.69
    IntoConstraints
    -0.68
     estekak
    -0.68
     Италијани
    -0.68
    Хьажоргаш
    -0.67
    KommentareTeilen
    -0.66
    цездатний
    -0.64
    RectangleBorder
    -0.64
    POSITIVE LOGITS
    JsonFormat
    0.36
     =
    0.34
    ValueStyle
    0.33
     Lo
    0.33
    3
    0.32
     adesi
    0.31
     $
    0.31
    2
    0.31
     clear
    0.31
     
    0.31
    Act Density 0.025%

    No Known Activations