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

    Neuronpedia

    INDEX
    Explanations

    references to objects or instances in code or documentation

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

    reference to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     OkHttpClient
    -0.59
    новништво
    -0.46
    UserScript
    -0.46
    Combined
    -0.39
    Overall
    -0.39
    Rolling
    -0.38
    Concer
    -0.37
    Reason
    -0.37
    Conduct
    -0.37
    AnimationsModule
    -0.37
    POSITIVE LOGITS
     reference
    1.01
     references
    0.90
    reference
    0.87
     Reference
    0.87
    Reference
    0.81
     References
    0.80
     REFERENCE
    0.80
    references
    0.78
     REFERENCES
    0.72
    getReference
    0.71
    Act Density 0.139%

    No Known Activations