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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stringent
    -0.06
    _df
    -0.06
    stri
    -0.06
    泊
    -0.06
    Degree
    -0.06
     riots
    -0.06
     factor
    -0.06
     routed
    -0.06
     accus
    -0.06
     IPO
    -0.06
    POSITIVE LOGITS
    legt
    0.07
    _imm
    0.06
    še
    0.06
    účast
    0.06
    อห
    0.06
     х
    0.06
     QTest
    0.06
     волос
    0.06
     akci
    0.06
     Αλ
    0.06
    Act Density 0.020%

    No Known Activations