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

    Neuronpedia

    INDEX
    Explanations

    descriptions of parts and shapes in technical documents

    oai_token-act-pair · gemini-2.0-flash

    words related to openings or gaps

    np_token-act-pair-logits · gpt-4o-mini

    openings and holes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.68
    EndContext
    -0.63
    حياته
    -0.61
    InstrumentedTest
    -0.57
     dAtA
    -0.54
    fromnode
    -0.54
     мәкал
    -0.53
     ✭✭
    -0.52
    Rhestr
    -0.50
    ंदीखरीदारी
    -0.49
    POSITIVE LOGITS
     opening
    1.73
     openings
    1.73
     holes
    1.70
     hole
    1.70
    opening
    1.52
    holes
    1.49
     Hole
    1.48
     OPENING
    1.48
     Opening
    1.48
    Opening
    1.46
    Act Density 4.007%

    No Known Activations