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

    Neuronpedia

    INDEX
    Explanations

    organizational titles and specific departmental affiliations

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

    organizational units and roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     letz
    -0.29
     valoraciones
    -0.28
     compacto
    -0.28
     literario
    -0.28
     orgánico
    -0.28
     casada
    -0.28
     ajustado
    -0.28
     doppia
    -0.28
     religione
    -0.28
     Utilizamos
    -0.27
    POSITIVE LOGITS
    <unused7>
    0.76
    <unused8>
    0.75
    <unused23>
    0.75
    <unused93>
    0.75
    <unused16>
    0.75
    [@BOS@]
    0.75
    <unused47>
    0.75
    <unused68>
    0.75
    <unused3>
    0.75
    <unused14>
    0.75
    Act Density 0.073%

    No Known Activations