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

    Neuronpedia

    INDEX
    Explanations

    questions starting with "Why."

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

    Questions starting with "Why"

    np_acts-logits-general · gemini-2.0-flash

    why questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Datuak
    -1.02
    mybatisplus
    -0.95
    httphttps
    -0.94
    IntoConstraints
    -0.89
    UnusedPrivate
    -0.88
     AssemblyCompany
    -0.87
    ecap
    -0.86
    expandindo
    -0.85
    MLLoader
    -0.85
     unknownFields
    -0.84
    POSITIVE LOGITS
     they
    0.77
     exactly
    0.76
     pay
    0.71
     not
    0.71
     else
    0.70
     we
    0.67
     it
    0.65
     would
    0.65
     did
    0.64
     didn
    0.61
    Act Density 0.030%

    No Known Activations