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

    Neuronpedia

    INDEX
    Explanations

    specific measurements and dimensions related to physical objects and their properties

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

    Refers to "length" or distances

    np_acts-logits-general · gemini-2.0-flash

    length and distance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Cyfarwyddwr
    -0.42
    gaw
    -0.38
    gender
    -0.36
    Население
    -0.36
     mask
    -0.36
     gender
    -0.35
     Gates
    -0.35
     lymphocyte
    -0.34
     actionMode
    -0.34
    ourcen
    -0.34
    POSITIVE LOGITS
     length
    0.90
     lengths
    0.87
     Length
    0.76
     distance
    0.71
    Length
    0.71
     panjang
    0.69
     LENGTH
    0.68
     longueur
    0.66
     distances
    0.66
     Länge
    0.65
    Act Density 0.552%

    No Known Activations