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

    Neuronpedia

    INDEX
    Explanations

    references to new concepts or entities

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

    newly created or existing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -0.56
     незавершена
    -0.47
    ьаж
    -0.45
    ReadByte
    -0.43
    StructEnd
    -0.41
     createState
    -0.40
    AsUp
    -0.38
     Kuh
    -0.37
    enek
    -0.36
     nonUne
    -0.36
    POSITIVE LOGITS
     חיצוניים
    0.61
     newfound
    0.58
    Autoritní
    0.56
    MigrationBuilder
    0.53
     nuevo
    0.52
     newly
    0.52
    ngdoc
    0.52
    перь
    0.51
     nueva
    0.51
    Newly
    0.51
    Act Density 0.171%

    No Known Activations