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

    Neuronpedia

    INDEX
    Explanations

    edited

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     overdue
    -0.07
    евич
    -0.07
    dale
    -0.07
    -frequency
    -0.07
     Championship
    -0.07
    公社
    -0.07
    😕
    -0.06
    太极拳
    -0.06
     Fathers
    -0.06
     Sammy
    -0.06
    POSITIVE LOGITS
     orb
    0.07
    擬
    0.07
    oreach
    0.07
     PERF
    0.07
    .FlatStyle
    0.07
     고
    0.07
     alo
    0.07
    .IsAny
    0.07
    会影响
    0.07
     governors
    0.06
    Act Density 0.002%

    No Known Activations