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

    Neuronpedia

    INDEX
    Explanations

    servers and networking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Penn
    -0.07
    _validate
    -0.06
    _common
    -0.06
    lbs
    -0.06
    lain
    -0.06
    폭
    -0.06
    이라는
    -0.06
     autopsy
    -0.06
    遠
    -0.06
    stein
    -0.06
    POSITIVE LOGITS
     клуб
    0.07
    	Description
    0.07
     dec
    0.07
     fencing
    0.06
    (Exception
    0.06
    MethodBeat
    0.06
    Tit
    0.06
    pired
    0.06
    。",↵
    0.06
     bere
    0.06
    Act Density 0.031%

    No Known Activations