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

    Neuronpedia

    INDEX
    Explanations

    terms and events related to keyboard and touch interactions

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

    action completed or released

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused43>
    -0.77
    [@BOS@]
    -0.77
    <unused8>
    -0.77
    <unused3>
    -0.77
    <unused14>
    -0.77
    <unused79>
    -0.77
    <unused51>
    -0.77
    <unused74>
    -0.77
    <unused52>
    -0.77
    <unused16>
    -0.76
    POSITIVE LOGITS
    mouseup
    0.47
     lendemain
    0.35
     sonrası
    0.33
     after
    0.33
     jälkeen
    0.30
     после
    0.30
     onOptions
    0.29
     setelah
    0.29
     después
    0.28
    BeginInit
    0.28
    Act Density 0.006%

    No Known Activations