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

    Neuronpedia

    INDEX
    Explanations

    shutdown /r /t

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     suck
    0.36
    prd
    0.33
    非法
    0.33
     #-}
    0.32
     Robertson
    0.32
    anser
    0.32
     coef
    0.32
    Robertson
    0.32
    elfalt
    0.32
    퐶
    0.32
    POSITIVE LOGITS
     Gleich
    0.39
     rail
    0.37
     decrement
    0.36
     byte
    0.36
     decreasing
    0.35
    Trains
    0.35
     Trains
    0.34
     learning
    0.34
     нис
    0.34
     शीतल
    0.33
    Act Density 0.002%

    No Known Activations