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

    Neuronpedia

    INDEX
    Explanations

    symbols or punctuation that signify positive expressions or reactions

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

    <start_of_turn> user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    原
    -0.43
     oluşan
    -0.42
     recibido
    -0.41
     cambiado
    -0.41
     
    -0.40
     quedado
    -0.40
     mohl
    -0.40
     necesaria
    -0.40
     potřeb
    -0.40
     steder
    -0.39
    POSITIVE LOGITS
     autorytatywna
    0.93
    #+#
    0.92
     defaultstate
    0.90
    httphttps
    0.90
     pinulongan
    0.88
     CreateTagHelper
    0.88
    Datuak
    0.85
    0.85
    :+
    0.83
     незавершена
    0.83
    Act Density 0.000%

    No Known Activations