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

    Neuronpedia

    INDEX
    Explanations

    generate

    np_max-act-logits · gemini-2.5-flash-lite

    References to the assistant or model itself—questions about its capabilities, access (APIs/downloads), or self-descriptions.

    oai_token-act-pair · gpt-5-miniTriggered by @fornasiereraffaello
    New Auto-Interp
    Negative Logits
    姣
    0.52
    wedge
    0.50
     hydraul
    0.50
     etched
    0.49
     aisl
    0.49
     observers
    0.48
     grower
    0.47
    ascular
    0.46
     OnTrigger
    0.46
     पदाधिकारी
    0.46
    POSITIVE LOGITS
     generate
    1.39
    生成
    1.35
     Generate
    1.35
    Generate
    1.34
    Summar
    1.32
     generation
    1.31
     generating
    1.29
     Summar
    1.29
    generate
    1.27
     generación
    1.26
    Act Density 1.978%

    No Known Activations