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

    Neuronpedia

    INDEX
    Explanations

    technical terminology related to validation and filtering processes in data

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

    calibration, correlation, interpolation, error, debiasing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GraphicsUnit
    -0.68
    colgroup
    -0.61
    RegistryLite
    -0.59
     AssemblyProduct
    -0.59
    outWeight
    -0.58
     AssemblyCompany
    -0.55
     Administrativna
    -0.55
    GEBURTSDATUM
    -0.55
    interopRequire
    -0.53
     تضيفلها
    -0.52
    POSITIVE LOGITS
    expandindo
    0.49
     cár
    0.41
     stund
    0.40
    Captured
    0.39
     coordination
    0.38
    Handlers
    0.37
     Secund
    0.37
    开
    0.36
    Imp
    0.36
     action
    0.36
    Act Density 0.143%

    No Known Activations