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

    Neuronpedia

    INDEX
    Explanations

    auxiliary verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     was
    -0.09
     had
    -0.09
     were
    -0.08
    Occurred
    -0.08
     came
    -0.07
    .tk
    -0.07
    '´
    -0.07
     did
    -0.06
     depended
    -0.06
     était
    -0.06
    POSITIVE LOGITS
     msg
    0.07
     sorun
    0.07
    Ear
    0.06
     xrange
    0.06
    090
    0.06
     gadget
    0.06
    getUser
    0.06
    uilder
    0.06
    љ
    0.06
    .Has
    0.06
    Act Density 0.317%

    No Known Activations