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

    Neuronpedia

    INDEX
    Explanations

    Parentheses and dashes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vastaan
    -0.08
     atualmente
    -0.07
     lifespan
    -0.07
    .nc
    -0.07
     proliferation
    -0.07
     interdum
    -0.07
     sustain
    -0.07
     nges
    -0.07
    plode
    -0.07
     hyperlink
    -0.07
    POSITIVE LOGITS
     Greenwich
    0.08
     Mär
    0.08
     positiven
    0.08
    datum
    0.08
     positiva
    0.08
    374
    0.07
    -angle
    0.07
     blazing
    0.07
    ुल्क
    0.07
    _angle
    0.07
    Act Density 0.017%

    No Known Activations