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

    Neuronpedia

    INDEX
    Explanations

    conditional statements in code

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

    programming control flow statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     MainAxisSize
    -0.81
    <unused41>
    -0.81
    <unused16>
    -0.81
    [@BOS@]
    -0.81
    <unused51>
    -0.81
    <unused23>
    -0.81
    <unused43>
    -0.81
    <unused28>
    -0.81
    <unused8>
    -0.81
    <unused14>
    -0.81
    POSITIVE LOGITS
     deportivo
    0.31
     nostru
    0.29
     alternativo
    0.27
     financiero
    0.26
     Komunikasi
    0.26
     amargo
    0.25
     navideño
    0.24
     république
    0.24
     nocturno
    0.24
     funcionamento
    0.24
    Act Density 0.012%

    No Known Activations