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

    Neuronpedia

    INDEX
    Explanations

    terms related to spatial relationships and separations

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

    ways and separation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Blackburn
    -0.44
    дото
    -0.39
    ir
    -0.38
    ur
    -0.37
    lin
    -0.36
    li
    -0.35
    le
    -0.34
    зира
    -0.33
    ut
    -0.33
    ri
    -0.33
    POSITIVE LOGITS
     cách
    2.56
     Cách
    1.82
    cách
    1.77
    Cách
    1.57
    SequentialGroup
    0.82
    cach
    0.77
    posób
    0.75
    วิธี
    0.74
     Ways
    0.71
     cach
    0.70
    Act Density 0.001%

    No Known Activations