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

    Neuronpedia

    INDEX
    Explanations

    specific statistical or mathematical terms and conditional phrases

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

    goes to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hawatir
    -0.32
     ardından
    -0.29
    resh
    -0.29
     ontvang
    -0.28
     recognised
    -0.28
     yalnızca
    -0.28
     bahawa
    -0.28
    utili
    -0.28
     principio
    -0.28
     службы
    -0.28
    POSITIVE LOGITS
    OGND
    0.82
    AccessorTable
    0.71
     للمعارف
    0.69
    MessageOf
    0.62
     يتيمه
    0.62
     utafitiHapana
    0.60
    Kjelder
    0.60
    MemoryWarning
    0.59
    قایناقلار
    0.57
    endphp
    0.56
    Act Density 0.080%

    No Known Activations