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

    Neuronpedia

    INDEX
    Explanations

    specific terms related to physical objects or their characteristics

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

    usb mixer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.48
     telefónica
    -0.47
     człowie
    -0.46
     niebla
    -0.43
     mijne
    -0.42
     fidélité
    -0.42
     spéciaux
    -0.41
    UpInside
    -0.41
    новништво
    -0.40
     conseillé
    -0.40
    POSITIVE LOGITS
     Italijanski
    0.67
     betweenstory
    0.55
    AnimationsModule
    0.52
    ôtel
    0.51
    Numerology
    0.50
     Réponses
    0.48
    Autoritní
    0.48
    tagHelperRunner
    0.47
     noDo
    0.46
    hithe
    0.46
    Act Density 0.001%

    No Known Activations