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

    Neuronpedia

    INDEX
    Explanations

    uper

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ノ
    -0.07
    oston
    -0.06
     mysl
    -0.06
    -sample
    -0.06
    usz
    -0.06
    ">',↵
    -0.06
    urons
    -0.05
    ston
    -0.05
     kurtul
    -0.05
    �
    -0.05
    POSITIVE LOGITS
     cref
    0.11
     VB
    0.08
    ipers
    0.08
    (nameof
    0.08
     gem
    0.07
     Mouth
    0.07
    ")));
    0.07
     TERMS
    0.07
     Attendance
    0.07
     Beauty
    0.07
    Act Density 0.001%

    No Known Activations