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

    Neuronpedia

    INDEX
    Explanations

    terms related to uncertainty or absence of clarity in various contexts

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

    followed by the prefix "un" or "non."

    np_acts-logits-general · gemini-2.0-flash

    un- or non- states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Autoritní
    -1.07
     autorytatywna
    -0.83
    msgTypes
    -0.81
    PYX
    -0.77
    MigrationBuilder
    -0.77
     Wicidata
    -0.77
     propOrder
    -0.76
    -0.75
     &___
    -0.73
    IBOutlet
    -0.73
    POSITIVE LOGITS
     un
    2.08
     Un
    1.70
    Un
    1.65
     uns
    1.63
    un
    1.62
     unre
    1.54
     unt
    1.50
     non
    1.48
     Uns
    1.40
     une
    1.40
    Act Density 1.080%

    No Known Activations