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

    Neuronpedia

    INDEX
    Explanations

    >

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Enh
    -0.06
    洞
    -0.06
     Nack
    -0.06
    殊
    -0.06
    �
    -0.06
     Ninh
    -0.06
     Negro
    -0.06
     Essen
    -0.06
     Exhib
    -0.06
     NHS
    -0.06
    POSITIVE LOGITS
    _RADIUS
    0.07
    cie
    0.07
    >t
    0.07
     frequ
    0.07
    Rect
    0.07
     πλη
    0.06
     tổng
    0.06
    
    0.06
    xCB
    0.06
    eselect
    0.06
    Act Density 0.010%

    No Known Activations