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

    Neuronpedia

    INDEX
    Explanations

    technical terms and components related to manufacturing and mechanical processes

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

    Ends, edges, tips, or extensions

    np_acts-logits-general · gemini-2.0-flash

    edges, ends, extensions, portions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dominal
    -0.58
     MediatR
    -0.53
     panes
    -0.53
    charter
    -0.53
    Parcelize
    -0.51
    ſicht
    -0.50
     belts
    -0.50
    ThroughAttribute
    -0.50
    expandindo
    -0.50
    cables
    -0.50
    POSITIVE LOGITS
     edge
    0.63
     Spitze
    0.57
     edges
    0.57
     ends
    0.56
     ujung
    0.51
    edge
    0.51
    extrémité
    0.49
     extension
    0.49
     extensions
    0.48
    端
    0.46
    Act Density 0.776%

    No Known Activations