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

    Neuronpedia

    INDEX
    Explanations

    mathematics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     transient
    -0.08
    άνα
    -0.07
    udget
    -0.06
     Metro
    -0.06
     squid
    -0.06
    .at
    -0.06
    Georgia
    -0.06
     older
    -0.06
    (H
    -0.06
    (loc
    -0.06
    POSITIVE LOGITS
    validated
    0.07
     عندما
    0.06
     balık
    0.06
    ernals
    0.06
    <Scalars
    0.06
     bakeca
    0.06
     dac
    0.06
     condemned
    0.06
     ReferentialAction
    0.06
     çıkart
    0.06
    Act Density 0.004%

    No Known Activations