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

    Neuronpedia

    INDEX
    Explanations

    code, data structures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     agricultural
    -0.07
    瑟
    -0.07
     piel
    -0.07
    '},
    -0.06
     duplex
    -0.06
     Alma
    -0.06
    Ar
    -0.06
     inefficient
    -0.06
     Castro
    -0.06
     resident
    -0.06
    POSITIVE LOGITS
     ','.
    0.07
    /exec
    0.06
     không
    0.06
     kia
    0.06
    /*@
    0.06
     真
    0.06
    _CYCLE
    0.06
    	assertFalse
    0.06
    ่าจะ
    0.06
    ---------↵
    0.06
    Act Density 0.020%

    No Known Activations