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

    Neuronpedia

    INDEX
    Explanations

    terminal commands and finalization statements in code

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

    finally or out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -0.94
    ########.
    -0.83
    Tikang
    -0.82
    niſſe
    -0.79
    ſelf
    -0.78
    <unused79>
    -0.78
    <unused14>
    -0.77
    <unused41>
    -0.77
    <unused8>
    -0.77
    [@BOS@]
    -0.77
    POSITIVE LOGITS
    finally
    0.56
     finally
    0.41
    Finally
    0.39
     limpio
    0.37
     Finally
    0.35
     circonstances
    0.32
    TRAILING
    0.32
     secundario
    0.31
    try
    0.31
     hidrá
    0.31
    Act Density 0.001%

    No Known Activations