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

    Neuronpedia

    INDEX
    Explanations

    instances of guidance or illustrative examples in communication

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

    example and model

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     extra
    -0.34
    CardModule
    -0.31
    мум
    -0.31
     linh
    -0.30
    entr
    -0.30
     akin
    -0.29
     cumbersome
    -0.29
    絞
    -0.29
    autorest
    -0.29
     crisis
    -0.29
    POSITIVE LOGITS
     EXAMPLE
    0.75
    httphttps
    0.73
     exempl
    0.70
    OGND
    0.70
     estekak
    0.69
    rungsseite
    0.68
     ejemplar
    0.68
    Personendaten
    0.67
    exemplar
    0.67
     Vorbild
    0.65
    Act Density 0.030%

    No Known Activations