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

    Neuronpedia

    INDEX
    Explanations

    references to statistical data or estimations

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

    closing punctuation followed by a word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bootstrapcdn
    -0.84
    PerformLayout
    -0.73
     $_(
    -0.71
    styleType
    -0.70
    +#+#
    -0.69
    Aholisi
    -0.69
    tagHelperRunner
    -0.68
    ፩
    -0.66
    хьтан
    -0.66
    celotti
    -0.65
    POSITIVE LOGITS
     consulté
    0.38
     istrinya
    0.35
     prosjek
    0.35
     således
    0.34
     finnas
    0.34
     ibunya
    0.32
    ])),
    0.31
     époux
    0.31
     hierzu
    0.30
     svoju
    0.30
    Act Density 4.941%

    No Known Activations