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

    Neuronpedia

    INDEX
    Explanations

    Names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sleeve
    -0.06
     balancing
    -0.06
    	SP
    -0.06
     Db
    -0.06
     tls
    -0.06
    	boost
    -0.06
    Intermediate
    -0.06
    (express
    -0.06
    (CON
    -0.06
    580
    -0.05
    POSITIVE LOGITS
    ologické
    0.07
     zvuky
    0.07
     Поч
    0.06
     Olomou
    0.06
    enterprise
    0.06
    Cas
    0.06
    變
    0.06
    .dao
    0.06
     نیروی
    0.06
     našich
    0.06
    Act Density 0.014%

    No Known Activations