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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate contrasts or comparisons

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

    importance or significance

    np_acts-logits-general · gemini-2.0-flash

    most importantly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wiktionnaire
    -0.72
    Diweddarwch
    -0.59
    ExecuteReader
    -0.59
     nahilalakip
    -0.58
    ]=>
    -0.58
     typelib
    -0.58
    jooq
    -0.58
     viewType
    -0.57
    Referencie
    -0.56
     resourceCulture
    -0.56
    POSITIVE LOGITS
     most
    2.42
    most
    1.96
     importantly
    1.85
    Most
    1.78
     MOST
    1.74
     Most
    1.74
    MOST
    1.59
    何より
    1.59
     surtout
    1.46
     самое
    1.40
    Act Density 0.287%

    No Known Activations