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

    Neuronpedia

    INDEX
    Explanations

    data structures and metadata associated with software dependencies and configurations

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

    Metadata keys and values

    np_acts-logits-general · gemini-2.0-flash

    metadata keys and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    !
    -0.48
     
    -0.47
    zeugen
    -0.45
    <eos>
    -0.45
     Dear
    -0.44
    ;
    -0.44
    ,
    -0.44
    Dear
    -0.41
     with
    -0.41
     +
    -0.41
    POSITIVE LOGITS
    rungsseite
    1.21
     nahilalakip
    1.17
    setVerticalGroup
    1.13
    Datuak
    1.12
    +#+#
    1.12
     Roskov
    1.11
    Hozzáférés
    1.10
     CreateTagHelper
    1.06
    featureID
    1.06
     resourceCulture
    1.05
    Act Density 0.508%

    No Known Activations