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

    Neuronpedia

    INDEX
    Explanations

    structured data and programming syntax

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

    Special tongue, explores further

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Administrativna
    -0.90
    MigrationBuilder
    -0.81
     Italijani
    -0.77
    <unused16>
    -0.77
    <unused23>
    -0.77
    <unused28>
    -0.76
    <unused43>
    -0.76
    <unused14>
    -0.76
    [@BOS@]
    -0.76
    <unused8>
    -0.76
    POSITIVE LOGITS
     pool
    0.32
     Bat
    0.29
     Neu
    0.28
     كل
    0.28
     sc
    0.28
    Pool
    0.27
    To
    0.26
     
    0.26
    Need
    0.26
    ↵↵
    0.25
    Act Density 0.132%

    No Known Activations