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

    Neuronpedia

    INDEX
    Explanations

    programming constructs related to debugging or variable management

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

    checkboxes unchecked

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     femininas
    -0.29
     verdade
    -0.28
     theoretical
    -0.26
     feminina
    -0.26
     dzien
    -0.26
     scra
    -0.25
     estimés
    -0.24
     piece
    -0.24
     boneco
    -0.23
     dezembro
    -0.23
    POSITIVE LOGITS
    AndEndTag
    0.81
    TagMode
    0.81
    ंदीखरीदारी
    0.80
    ":[{
    0.76
    EndInit
    0.74
    tangentMode
    0.73
     resourceCulture
    0.73
    PreInfinity
    0.72
    OGND
    0.68
    HideFlags
    0.68
    Act Density 0.389%

    No Known Activations