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

    Neuronpedia

    INDEX
    Explanations

    adorned

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     uncont
    -0.07
     mercy
    -0.07
    volt
    -0.07
    十二
    -0.07
     эффектив
    -0.06
    电
    -0.06
    roadcast
    -0.06
    Fuck
    -0.06
    -oper
    -0.06
    iếu
    -0.06
    POSITIVE LOGITS
     adorned
    0.12
     adorn
    0.11
     proč
    0.08
    飾
    0.07
     draped
    0.07
     embell
    0.07
     trang
    0.07
    .scalatest
    0.06
    'nde
    0.06
     trimmed
    0.06
    Act Density 0.010%

    No Known Activations