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

    Neuronpedia

    INDEX
    Explanations

    precise

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     attractive
    -0.07
    kg
    -0.07
    dogs
    -0.07
    .Get
    -0.07
     Dogs
    -0.07
    dog
    -0.06
     average
    -0.06
    ++++++++
    -0.06
    -average
    -0.06
     sk
    -0.06
    POSITIVE LOGITS
     precise
    0.18
     precisely
    0.15
     precision
    0.11
     Precision
    0.09
    Precision
    0.09
    prec
    0.09
     precis
    0.08
    precision
    0.08
     pinpoint
    0.08
     ми
    0.08
    Act Density 0.012%

    No Known Activations