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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -pres
    -0.07
     sahiptir
    -0.07
    -rest
    -0.06
    _transfer
    -0.06
    sta
    -0.06
    Teams
    -0.06
     oe
    -0.06
    ِل
    -0.06
    boxes
    -0.06
    avors
    -0.06
    POSITIVE LOGITS
    ﺎ
    0.07
     elapsed
    0.07
     Passenger
    0.07
    �
    0.06
     Leave
    0.06
    Suddenly
    0.06
     throwing
    0.06
     extr
    0.06
     enrich
    0.06
     Promo
    0.06
    Act Density 0.070%

    No Known Activations