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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     superficial
    -0.07
     sửa
    -0.07
     microscopic
    -0.07
    Hot
    -0.07
    響
    -0.07
    ﮥ
    -0.06
     expert
    -0.06
    -0.06
    -0.06
    玺
    -0.06
    POSITIVE LOGITS
    -cap
    0.07
    vice
    0.07
     Kunden
    0.07
    وخ
    0.07
     لبنان
    0.07
     MOS
    0.07
     Optional
    0.06
     Vanguard
    0.06
     mudança
    0.06
    trys
    0.06
    Act Density 0.048%

    No Known Activations