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

    Neuronpedia

    INDEX
    Explanations

    asking what something is like

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    לי
    0.72
    ס
    0.72
    ק
    0.66
    ทาง
    0.65
    YEAR
    0.64
    ubu
    0.64
    ווה
    0.64
    т
    0.62
    ो
    0.62
    ्हे
    0.61
    POSITIVE LOGITS
     cerebellar
    0.64
    មាន
    0.62
    i
    0.61
    \
    0.61
    <0x82>
    0.60
     phospholipid
    0.60
    <0x80>
    0.60
     generalized
    0.59
     recognizes
    0.59
     moisturizing
    0.59
    Act Density 0.001%

    No Known Activations