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

    Neuronpedia

    INDEX
    Explanations

    references to energy and thermodynamic principles

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

    Energy changes and differences

    np_acts-logits-general · gemini-2.0-flash

    energy changes and differences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Weekly
    -0.44
     surat
    -0.44
    נה
    -0.41
     Flanagan
    -0.40
     démoc
    -0.39
    واد
    -0.39
    月
    -0.38
    lyn
    -0.38
     cilind
    -0.38
    шер
    -0.37
    POSITIVE LOGITS
    脚注の使い方
    1.17
    RenderAtEndOf
    1.10
    expandindo
    1.06
     protoimpl
    1.06
    BufferException
    1.06
     CreateTagHelper
    1.01
    1.00
     resourceCulture
    0.99
    sizeCache
    0.99
     energy
    0.98
    Act Density 0.671%

    No Known Activations