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

    Neuronpedia

    INDEX
    Explanations

    side length

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ીને
    -0.08
    ುವುದ
    -0.07
     बातचीत
    -0.07
    -Y
    -0.07
    会议
    -0.07
    银行
    -0.07
     банков
    -0.07
     היום
    -0.07
     발표
    -0.07
    ాగా
    -0.07
    POSITIVE LOGITS
     enchanting
    0.09
     Lotto
    0.09
     nx
    0.09
     cruises
    0.09
     ferry
    0.09
     entlang
    0.09
     trok
    0.08
     abaste
    0.08
     upgrading
    0.08
     enchant
    0.08
    Act Density 0.015%

    No Known Activations