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

    Neuronpedia

    INDEX
    Explanations

    Astronomical Units (AU)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Severity
    -0.07
     severe
    -0.07
    arm
    -0.07
     suffering
    -0.07
     Sav
    -0.07
    etras
    -0.07
    part
    -0.07
    Ign
    -0.07
     Severe
    -0.07
    Contr
    -0.07
    POSITIVE LOGITS
     malé
    0.10
     Yusuf
    0.09
     bibliography
    0.08
     estil
    0.08
     adventures
    0.08
     साह
    0.08
     =)↵↵
    0.08
     Campe
    0.08
     handful
    0.08
     myst
    0.08
    Act Density 0.001%

    No Known Activations