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

    Neuronpedia

    INDEX
    Explanations

    same

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    criptive
    -0.07
     Ferdinand
    -0.07
    ，要
    -0.06
     دین
    -0.06
    LocalizedMessage
    -0.06
    เอง
    -0.06
    routing
    -0.06
     Market
    -0.06
     promoter
    -0.06
    UFACT
    -0.06
    POSITIVE LOGITS
    AZ
    0.06
    .Α
    0.06
     beams
    0.06
     Чер
    0.06
    oly
    0.06
    غل
    0.06
    $l
    0.06
    怒
    0.05
    /users
    0.05
     elsif
    0.05
    Act Density 0.016%

    No Known Activations