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

    Neuronpedia

    INDEX
    Explanations

    late time period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    WebVitals
    -0.59
    .";
    -0.49
     sienta
    -0.49
     ferons
    -0.46
    ardless
    -0.46
    verwijspagina
    -0.45
    bex
    -0.45
    serviceWorker
    -0.44
     Notation
    -0.43
    \#:
    -0.42
    POSITIVE LOGITS
     and
    1.78
    และ
    0.79
     và
    0.79
    性和
    0.75
    and
    0.72
     и
    0.71
     \&
    0.68
     및
    0.64
     &
    0.63
     และ
    0.63
    Act Density 0.006%

    No Known Activations