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

    Neuronpedia

    INDEX
    Explanations

    embed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	d
    -0.06
    ôn
    -0.06
    heck
    -0.06
     WHICH
    -0.06
    _j
    -0.06
    _CART
    -0.06
     intersection
    -0.06
    _Log
    -0.06
    434
    -0.06
    _cached
    -0.06
    POSITIVE LOGITS
     Magnet
    0.07
     pervasive
    0.07
    .ReadByte
    0.07
    _nonce
    0.06
     policy
    0.06
     운영자
    0.06
     rusty
    0.06
    etě
    0.06
     uphol
    0.06
    ,
    0.06
    Act Density 0.005%

    No Known Activations