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

    Neuronpedia

    INDEX
    Explanations

    concepts related to legality and governance, particularly around individual rights and institutional structures

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

    introducing contrasting ideas

    np_acts-logits-general · gemini-2.0-flash

    but

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    versy
    -0.56
    FTFY
    -0.53
    RegressionTest
    -0.53
    brokes
    -0.52
    vábbi
    -0.51
    ériale
    -0.50
    fasis
    -0.49
    mitives
    -0.49
    terscotch
    -0.49
    isStatic
    -0.49
    POSITIVE LOGITS
     but
    1.94
     tetapi
    1.47
    but
    1.42
     tapi
    1.39
     nhưng
    1.36
     pero
    1.36
     namun
    1.30
     maar
    1.25
    但
    1.14
     אך
    1.14
    Act Density 0.641%

    No Known Activations