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

    Neuronpedia

    INDEX
    Explanations

    sleep

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sided
    -0.07
     traveler
    -0.07
     cook
    -0.07
    uddy
    -0.06
    Miller
    -0.06
    enger
    -0.06
     suggested
    -0.06
    هار
    -0.06
    	ERROR
    -0.06
    卓
    -0.06
    POSITIVE LOGITS
    >An
    0.07
     jsme
    0.07
    beginTransaction
    0.07
    reur
    0.06
     daň
    0.06
    ひと
    0.06
     अस
    0.06
     �
    0.06
    ">$
    0.06
     specifically
    0.06
    Act Density 0.006%

    No Known Activations