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

    Neuronpedia

    INDEX
    Explanations

    references to emptiness or voids

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

    empty or blank followed by descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Audiodateien
    -0.45
     amable
    -0.44
     deber
    -0.43
     Constitucional
    -0.41
     Ambiental
    -0.41
     amables
    -0.41
     evolucion
    -0.40
     establecido
    -0.40
     ancak
    -0.40
    komp
    -0.40
    POSITIVE LOGITS
     empty
    0.98
     Empty
    0.95
     emptiness
    0.91
     EMPTY
    0.82
    empty
    0.78
    Empty
    0.77
     kosong
    0.71
     leeren
    0.70
     vacant
    0.69
     blank
    0.68
    Act Density 0.033%

    No Known Activations