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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating leadership or guidance

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

    paving the way for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ldorf
    -0.36
    posables
    -0.34
     وتسجيلات
    -0.33
     BoxFit
    -0.32
     Fic
    -0.32
     correos
    -0.32
     Psychiatric
    -0.32
    ┣
    -0.32
    umbai
    -0.32
     foreigners
    -0.32
    POSITIVE LOGITS
    Way
    0.56
     utafitiHapana
    0.54
     rhestr
    0.54
    ########.
    0.53
    readAs
    0.50
     '\\;'
    0.50
    GraphicsUnit
    0.50
     noastră
    0.50
     Vorbild
    0.50
     &___
    0.50
    Act Density 0.002%

    No Known Activations