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

    Neuronpedia

    INDEX
    Explanations

    discharged

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Worm
    -0.07
     Circular
    -0.07
     shredd
    -0.07
     Brotherhood
    -0.06
     Imperial
    -0.06
    .Out
    -0.06
    901
    -0.06
     Redemption
    -0.06
    Pull
    -0.06
    Circular
    -0.06
    POSITIVE LOGITS
    .tensor
    0.07
     lasc
    0.07
     discharged
    0.06
     disarm
    0.06
    di
    0.06
    タン
    0.06
    *******
↵
    0.06
     الآن
    0.06
     введ
    0.06
     parole
    0.06
    Act Density 0.004%

    No Known Activations