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

    Neuronpedia

    INDEX
    Explanations

    sleep environment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lui
    -0.07
     יל
    -0.07
     parents
    -0.07
    	with
    -0.07
    🍛
    -0.07
     lightweight
    -0.07
    ointment
    -0.07
    OTH
    -0.07
     clothing
    -0.07
     Web
    -0.06
    POSITIVE LOGITS
    בדק
    0.08
     Selling
    0.07
    enny
    0.07
    퍙
    0.07
    校区
    0.07
     paralysis
    0.07
    allery
    0.06
    seven
    0.06
     secrecy
    0.06
     explosion
    0.06
    Act Density 0.006%

    No Known Activations