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

    Neuronpedia

    INDEX
    Explanations

    conditions or types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    that
    0.50
    ка
    0.46
    Dari
    0.46
    晧
    0.45
    max
    0.44
    魔
    0.44
    нус
    0.43
    self
    0.43
    Max
    0.43
    I
    0.43
    POSITIVE LOGITS
     scandal
    0.52
     charity
    0.46
     Grundstück
    0.46
    >());
    0.45
     generator
    0.44
     dispensary
    0.44
     جنگ
    0.44
     certe
    0.44
     cupboard
    0.44
     pov
    0.44
    Act Density 0.001%

    No Known Activations