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

    Neuronpedia

    INDEX
    Explanations

    sequences of numerical data or values

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

    numbers followed by comma

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused41>
    -0.80
    <unused17>
    -0.80
    <unused79>
    -0.80
    <unused3>
    -0.80
    <unused16>
    -0.80
    [@BOS@]
    -0.80
    <unused23>
    -0.80
    <unused55>
    -0.80
    <unused52>
    -0.80
    <unused8>
    -0.79
    POSITIVE LOGITS
    ,
    0.37
     Privacidad
    0.28
     itself
    0.25
     frecuencia
    0.25
     retrait
    0.24
     eux
    0.24
     himself
    0.24
     становника
    0.24
     arbres
    0.23
    .,
    0.23
    Act Density 0.140%

    No Known Activations