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

    Neuronpedia

    INDEX
    Explanations

    x

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (IR
    -0.08
     ചെറിയ
    -0.08
     Tribunal
    -0.08
    arca
    -0.08
     belasting
    -0.08
     radically
    -0.08
     მცირე
    -0.08
    .remote
    -0.07
     pequenas
    -0.07
    शल
    -0.07
    POSITIVE LOGITS
     ponieważ
    0.09
     goals
    0.08
     förs
    0.07
     sytu
    0.07
     procedures
    0.07
     spac
    0.07
     lik
    0.07
     którym
    0.07
     reflux
    0.07
     hopp
    0.07
    Act Density 0.059%

    No Known Activations