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

    Neuronpedia

    INDEX
    Explanations

    tables

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     принадлеж
    -0.07
    _LOWER
    -0.06
    023
    -0.06
     coat
    -0.06
    _pad
    -0.06
    mh
    -0.06
     PROP
    -0.06
     범
    -0.06
    оу
    -0.06
    	Rect
    -0.06
    POSITIVE LOGITS
    married
    0.07
     Esc
    0.07
     useState
    0.07
    --------------------------------
    0.07
    LEMENT
    0.07
    mons
    0.07
    caught
    0.06
    son
    0.06
    sson
    0.06
    esta
    0.06
    Act Density 0.005%

    No Known Activations