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

    Neuronpedia

    INDEX
    Explanations

    keywords related to success and error messages in API responses

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

    error messages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nhiên
    -0.40
     normally
    -0.38
    DetailComponent
    -0.35
     ditemp
    -0.33
     statt
    -0.32
     elements
    -0.32
    agin
    -0.32
     facilities
    -0.32
     abstracts
    -0.32
    }`;
    -0.31
    POSITIVE LOGITS
     Jefus
    0.79
     Anſ
    0.77
    ########.
    0.73
    featureID
    0.72
     Monfieur
    0.68
     &___
    0.67
     Chrift
    0.66
     Chriſt
    0.66
     AssemblyTitle
    0.65
     Verſ
    0.63
    Act Density 0.005%

    No Known Activations