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

    Neuronpedia

    INDEX
    Explanations

    guess

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    疽
    -0.07
    _PROCESS
    -0.07
    	move
    -0.07
    连续
    -0.07
    +"'
    -0.07
     Web
    -0.07
    _BY
    -0.07
    腴
    -0.06
    \Requests
    -0.06
    .validate
    -0.06
    POSITIVE LOGITS
    (ff
    0.07
    くだ
    0.07
    广播电视
    0.07
    CLI
    0.07
    꽝
    0.07
     affiliation
    0.06
     derog
    0.06
    昭
    0.06
     intellig
    0.06
     chlor
    0.06
    Act Density 0.016%

    No Known Activations