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

    Neuronpedia

    INDEX
    Explanations

    technical and programming-related topics

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

    code blocks and data structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Мексичка
    -0.30
     centímetros
    -0.29
     Савезне
    -0.29
     razón
    -0.29
     jelasnya
    -0.29
     autorytatywna
    -0.29
     diagnosis
    -0.28
     indifer
    -0.28
     Ähnliche
    -0.28
    htbp
    -0.28
    POSITIVE LOGITS
    MLLoader
    0.77
     ujednoznacz
    0.75
     الحره
    0.66
    [@BOS@]
    0.65
    <unused8>
    0.65
    <unused3>
    0.65
    <unused42>
    0.65
    <unused43>
    0.65
    <unused74>
    0.65
    <pad>
    0.65
    Act Density 0.014%

    No Known Activations