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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     make
    -0.52
     is
    -0.50
     makes
    -0.50
     set
    -0.49
     allowed
    -0.49
    }*/
    -0.49
     sitio
    -0.48
    })$}
    -0.48
     contin
    -0.48
     also
    -0.47
    POSITIVE LOGITS
    titleMargin
    0.76
    OGND
    0.74
    WebVitals
    0.63
     kaarangay
    0.60
     grecque
    0.60
     AssemblyCompany
    0.60
    RegressionTest
    0.59
    ImageContext
    0.57
     asupra
    0.56
     young
    0.56
    Act Density 0.000%

    No Known Activations