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

    Neuronpedia

    INDEX
    Explanations

    sentences that contain ellipses or pauses

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

    references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    [?]
    -0.44
     byteArray
    -0.43
     [?]
    -0.43
     
    -0.43
    __(/*!
    -0.42
     vector
    -0.41
    </>
    -0.41
     Palo
    -0.41
    ]--;
    -0.41
     forestal
    -0.40
    POSITIVE LOGITS
     isInitialized
    0.59
     propOrder
    0.52
    uxxxx
    0.52
    انجليز
    0.48
     تعدى
    0.44
    iedene
    0.43
     navideña
    0.43
    Erreferentziak
    0.42
    Gesamt
    0.42
    enguaje
    0.42
    Act Density 0.017%

    No Known Activations