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

    Neuronpedia

    INDEX
    Explanations

    references to television shows

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

    show

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Italijani
    -0.57
    thanes
    -0.57
     Hanks
    -0.56
    teva
    -0.52
     statusCode
    -0.51
     clientId
    -0.50
    nci
    -0.50
    uxxxx
    -0.50
     ErrorCode
    -0.49
    nextElement
    -0.49
    POSITIVE LOGITS
     show
    1.70
    show
    1.66
     Show
    1.57
    Show
    1.50
     SHOW
    1.34
    SHOW
    1.21
     fhew
    1.07
     shew
    0.99
     Mostrar
    0.87
     шоу
    0.82
    Act Density 0.022%

    No Known Activations