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

    Neuronpedia

    INDEX
    Explanations

    possessive/plural

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     butcher
    -0.08
    agrant
    -0.07
     hath
    -0.07
     vyu
    -0.07
    .raise
    -0.06
     stál
    -0.06
     gebru
    -0.06
     حض
    -0.06
     divis
    -0.06
     حتی
    -0.06
    POSITIVE LOGITS
     полит
    0.07
     Intr
    0.07
     intr
    0.06
     Classified
    0.06
     Progressive
    0.06
     Progress
    0.06
     Industrial
    0.06
     Interviews
    0.06
    _stub
    0.06
     essays
    0.06
    Act Density 0.001%

    No Known Activations