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

    Neuronpedia

    INDEX
    Explanations

    postdoctoral academic researcher

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    le
    0.63
     D
    0.63
    ICC
    0.61
    Z
    0.59
    IAN
    0.58
     Интер
    0.57
    AY
    0.56
    Ž
    0.56
    Д
    0.55
     টাইম
    0.55
    POSITIVE LOGITS
    ва
    0.60
     kilowatt
    0.56
     fatality
    0.54
    膏
    0.52
    스는
    0.51
    <0x80>
    0.50
    testing
    0.50
     combust
    0.50
    人用
    0.50
     volition
    0.49
    Act Density 0.001%

    No Known Activations