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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mayo
    -0.07
     releasing
    -0.06
     AttributeSet
    -0.06
     Поп
    -0.06
    ��
    -0.06
     milit
    -0.06
     hacks
    -0.06
    ,…↵↵
    -0.06
     hype
    -0.06
     width
    -0.06
    POSITIVE LOGITS
    sizlik
    0.07
     demeanor
    0.06
    sense
    0.06
    memiş
    0.06
     setDefaultCloseOperation
    0.06
     SAR
    0.06
     ydk
    0.06
     předsed
    0.06
     ефектив
    0.06
    puted
    0.06
    Act Density 0.311%

    No Known Activations