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

    Neuronpedia

    INDEX
    Explanations

    }"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ou
    -0.07
     Colo
    -0.07
    .lot
    -0.07
     Cause
    -0.07
     jet
    -0.06
     kinky
    -0.06
     Voc
    -0.06
     Truman
    -0.06
     consistently
    -0.06
    КА
    -0.06
    POSITIVE LOGITS
     района
    0.07
    inars
    0.06
    INTERN
    0.06
     سطح
    0.06
    에서
    0.06
     calendar
    0.06
    cmath
    0.06
    _CANCEL
    0.06
    命周期
    0.06
    optimize
    0.05
    Act Density 0.001%

    No Known Activations