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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating caution or reliance on information

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

    medical advice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.59
    sizeCache
    -0.53
     utafitiHapana
    -0.52
    expandindo
    -0.52
     насељу
    -0.50
    GHIJKLM
    -0.49
    httphttps
    -0.49
    AccessorTable
    -0.49
     betweenstory
    -0.48
    TypedDataSet
    -0.48
    POSITIVE LOGITS
     Clube
    0.35
     MainAxisSize
    0.35
     kjem
    0.35
    presence
    0.34
     Ham
    0.33
    canadian
    0.33
    TagMode
    0.33
    compound
    0.32
     Selatan
    0.32
    standard
    0.32
    Act Density 0.001%

    No Known Activations