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

    Neuronpedia

    INDEX
    Explanations

    copyright/generated code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .percent
    -0.07
     prominent
    -0.07
    Constants
    -0.07
    .ID
    -0.07
    걀
    -0.07
    ellant
    -0.07
     expert
    -0.07
     ganz
    -0.07
    热带
    -0.07
     accomplish
    -0.07
    POSITIVE LOGITS
    レス
    0.07
    聱
    0.06
    .Course
    0.06
    ⾔
    0.06
     trx
    0.06
     Say
    0.06
    laş
    0.06
     Influence
    0.06
     warfare
    0.06
    铢
    0.06
    Act Density 0.001%

    No Known Activations