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

    Neuronpedia

    INDEX
    Explanations

    conversion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    埙
    -0.08
     contexts
    -0.07
    snow
    -0.07
    Suggestions
    -0.07
     Hurricanes
    -0.07
     Nimbus
    -0.07
    炽
    -0.07
     العرب
    -0.07
     Cobra
    -0.07
     Organization
    -0.07
    POSITIVE LOGITS
     kol
    0.07
    尽快
    0.07
     leak
    0.07
    水分
    0.06
     sorry
    0.06
     defective
    0.06
     sed
    0.06
     Pak
    0.06
     infiltr
    0.06
    瑃
    0.06
    Act Density 0.006%

    No Known Activations