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

    Neuronpedia

    INDEX
    Explanations

    numbers related to measurements or quantities

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

    code documentation comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    enumi
    -0.49
    __*/
    -0.47
     bó
    -0.47
     MainAxisSize
    -0.46
    Πηγές
    -0.45
    ->___
    -0.45
    loß
    -0.44
     destroyed
    -0.44
    нциклопедия
    -0.44
     Brenner
    -0.44
    POSITIVE LOGITS
    ?
    0.50
    ?</
    0.46
    </h3>
    0.45
    wasn
    0.45
    httphttps
    0.45
    ⓧ
    0.45
     ?</
    0.43
    </i>
    0.43
    LookAnd
    0.43
     calça
    0.43
    Act Density 0.007%

    No Known Activations