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

    Neuronpedia

    INDEX
    Explanations

    references to academic journals and articles

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

    . or user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     redacción
    -0.39
     compleja
    -0.34
     exploración
    -0.33
    élaboration
    -0.33
     contemporánea
    -0.33
     generasi
    -0.33
     Küste
    -0.32
     diversión
    -0.31
     amenazas
    -0.31
     tropas
    -0.31
    POSITIVE LOGITS
     estekak
    0.87
    BagConstraints
    0.77
     queſta
    0.75
    KommentareTeilen
    0.74
     समीक्षाओं
    0.73
    tagHelperRunner
    0.71
     BoxFit
    0.69
     ſche
    0.68
     виправивши
    0.67
    ſelf
    0.67
    Act Density 0.000%

    No Known Activations