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

    Neuronpedia

    INDEX
    Explanations

    blocks of code or segments in programming languages

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

    closing code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ftagPool
    -0.56
    ROIT
    -0.56
     kasarigan
    -0.53
     Penh
    -0.52
    yarnpkg
    -0.52
    TagMode
    -0.51
     незавершена
    -0.50
    󠁢
    -0.49
    tvb
    -0.47
    sätzlich
    -0.46
    POSITIVE LOGITS
     виправивши
    0.50
    AccessorTable
    0.43
    };*/
    0.42
    adaptiveStyles
    0.41
     pakan
    0.38
     votación
    0.38
    ambién
    0.37
    expandindo
    0.36
     kuiten
    0.35
    verwijspagina
    0.35
    Act Density 0.008%

    No Known Activations