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

    Neuronpedia

    INDEX
    Explanations

    references to "wire" and related types within a technical or programming context

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

    wire and related contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dps
    -0.41
     Katja
    -0.40
     Parenthood
    -0.38
     Huntingdon
    -0.38
     zdan
    -0.38
     Dazu
    -0.37
    ContextCompat
    -0.37
    creativecommons
    -0.36
    Pumpkin
    -0.36
    Mom
    -0.36
    POSITIVE LOGITS
     Wire
    2.69
    Wire
    2.67
     wire
    2.61
    wire
    2.52
     WIRE
    2.14
    WIRE
    1.94
     alambre
    1.43
     Draht
    1.39
     Wires
    1.28
     wires
    1.27
    Act Density 0.007%

    No Known Activations