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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lettuce
    -0.07
    mmc
    -0.06
    мами
    -0.06
    (tuple
    -0.06
     qualifies
    -0.06
    _cpp
    -0.06
     tesis
    -0.06
    �
    -0.06
    650
    -0.06
    acency
    -0.06
    POSITIVE LOGITS
     dress
    0.06
    ΕΛ
    0.06
     SWITCH
    0.06
     Worst
    0.06
    料無料
    0.06
     εν
    0.06
     benchmark
    0.06
    (":/
    0.06
     FIXED
    0.06
    ates
    0.06
    Act Density 0.426%

    No Known Activations