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

    Neuronpedia

    INDEX
    Explanations

    Japanese names with multiple parts

    oai_token-act-pair · gemini-2.0-flash

    specific names or technical terms

    np_token-act-pair-logits · gpt-4o-mini

    Japanese names/code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     recev
    -0.58
     препратки
    -0.57
    StructEnd
    -0.56
     leden
    -0.54
    SharedCtor
    -0.52
    LayoutStyle
    -0.51
     GridLayout
    -0.51
     محفوظة
    -0.50
    álja
    -0.50
     חיצוניים
    -0.48
    POSITIVE LOGITS
    ValueStyle
    0.54
    felves
    0.54
    uo
    0.52
    ThroughAttribute
    0.51
    utilisons
    0.50
    Népesség
    0.50
    enchymal
    0.44
    PropertyGroup
    0.44
    írez
    0.44
    memoized
    0.43
    Act Density 0.636%

    No Known Activations