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

    Neuronpedia

    INDEX
    Explanations

    instances of numeric values or identifiers

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

    El-Bushra

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ngdoc
    -0.70
     صوتيه
    -0.69
     PopupWindow
    -0.53
    PMailer
    -0.51
    RectangleBorder
    -0.51
    AddTagHelper
    -0.49
    bootstrapcdn
    -0.48
    Rhestr
    -0.48
     pulumi
    -0.47
    TagMode
    -0.46
    POSITIVE LOGITS
    もしれない
    0.36
     féminine
    0.36
    Birch
    0.35
     éditoriale
    0.35
    vish
    0.35
     ponownie
    0.35
    "}")
    0.35
     affari
    0.34
     écoulé
    0.34
    inaw
    0.34
    Act Density 0.016%

    No Known Activations