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

    Neuronpedia

    INDEX
    Explanations

    parts of code related to user interface dialog handling

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

    user input or query

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    المناصب
    -0.41
    typeDefinition
    -0.39
    MENAFN
    -0.38
     незавершена
    -0.37
     Roskov
    -0.36
     UIAlert
    -0.36
    tinyos
    -0.36
    Tembelea
    -0.36
    ьаж
    -0.35
    BeginInit
    -0.35
    POSITIVE LOGITS
     للاسماء
    0.63
     picioare
    0.46
     normalidad
    0.46
    fjspx
    0.44
     atriz
    0.43
     esternos
    0.43
     casada
    0.41
     willed
    0.41
     messed
    0.40
    #+#
    0.40
    Act Density 0.017%

    No Known Activations