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

    Neuronpedia

    INDEX
    Explanations

    repeated multi-character symbols or comment indicators in code

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

    user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -0.62
    -0.62
    TagMode
    -0.61
     Normdatei
    -0.60
     disambiguazione
    -0.59
     للمعارف
    -0.57
    AsUp
    -0.54
     Infórmanos
    -0.53
    orsese
    -0.52
    󠁣
    -0.52
    POSITIVE LOGITS
     *
    0.74
     *
    0.47
    +*
    0.45
     **
    0.44
     (*
    0.42
     *"
    0.41
    (*
    0.40
    LEGGI
    0.40
    >*
    0.40
    ("*
    0.37
    Act Density 0.095%

    No Known Activations