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

    Neuronpedia

    INDEX
    Explanations

    medical procedures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     추
    -0.08
     frustrated
    -0.08
     주
    -0.08
     misuse
    -0.07
     wages
    -0.07
    Used
    -0.07
    Recovered
    -0.07
    Such
    -0.07
    EH
    -0.07
     প্রত
    -0.07
    POSITIVE LOGITS
     beforehand
    0.16
     préalable
    0.15
    准备
    0.15
     לפני
    0.13
     préparer
    0.13
     preparação
    0.12
     Vorbereitung
    0.12
     prepar
    0.12
     preparación
    0.12
     prior
    0.12
    Act Density 0.043%

    No Known Activations