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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    ‎
    -0.06
    <S
    -0.06
     turnaround
    -0.06
    Carousel
    -0.06
     persuasion
    -0.06
     mixer
    -0.06
     января
    -0.06
     Brunswick
    -0.06
     После
    -0.06
    POSITIVE LOGITS
    ,),↵
    0.07
     fries
    0.06
    eper
    0.06
     mileage
    0.06
    Far
    0.06
     Far
    0.06
    nen
    0.06
     home
    0.06
     Lob
    0.06
    [len
    0.06
    Act Density 0.001%

    No Known Activations