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

    Neuronpedia

    INDEX
    Explanations

    say special characters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     konuş
    -0.07
    偾
    -0.07
    踮
    -0.07
    .gameserver
    -0.07
     конкр
    -0.06
    ("{}
    -0.06
    EXIT
    -0.06
     Paramount
    -0.06
    cré
    -0.06
    嘱
    -0.06
    POSITIVE LOGITS
    意味着
    0.08
    .Type
    0.07
    (TYPE
    0.07
     sympathy
    0.07
    QUERY
    0.07
     reinstall
    0.07
     contour
    0.07
     Equal
    0.07
    ಆ
    0.07
     español
    0.06
    Act Density 0.000%

    No Known Activations