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

    Neuronpedia

    INDEX
    Explanations

    sections of code within a programming context

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

    empty string assignments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    transQ
    -0.76
     للاسماء
    -0.64
    intios
    -0.60
    mentaux
    -0.58
     CreateTagHelper
    -0.56
     estadounid
    -0.54
     indígen
    -0.54
    principalTable
    -0.53
    autique
    -0.53
    featureID
    -0.52
    POSITIVE LOGITS
    EmptyString
    0.51
     blank
    0.44
     empty
    0.42
     "";
    0.41
    Empty
    0.41
     Empty
    0.40
    ="";
    0.39
    empty
    0.38
    blank
    0.36
     ["",
    0.36
    Act Density 0.016%

    No Known Activations