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

    Neuronpedia

    INDEX
    Explanations

    code and math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    翁
    -0.08
    朱
    -0.08
    øv
    -0.07
     jūs
    -0.07
    展
    -0.07
    意
    -0.07
     stabile
    -0.07
    mst
    -0.07
    Ti
    -0.07
    �
    -0.07
    POSITIVE LOGITS
    /or
    0.07
    Law
    0.07
    ennig
    0.07
    0.07
     indeed
    0.07
     hos
    0.07
    comings
    0.07
    -law
    0.07
     Indianapolis
    0.07
    هور
    0.07
    Act Density 0.530%

    No Known Activations