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

    Neuronpedia

    INDEX
    Explanations

    references to software versioning and version numbers

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

    major version

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ột
    -0.35
    hatikan
    -0.33
    NUMX
    -0.31
     CanadaChoose
    -0.31
    kadot
    -0.30
    ...');
    -0.29
     desierto
    -0.29
     asiatique
    -0.28
    verifyException
    -0.28
     ihres
    -0.28
    POSITIVE LOGITS
     Version
    1.18
     version
    0.96
     VERSION
    0.87
     Versions
    0.82
    Versión
    0.76
    version
    0.74
     versi
    0.73
     versions
    0.73
    Version
    0.73
     major
    0.71
    Act Density 0.002%

    No Known Activations