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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Axis
    -0.08
     parks
    -0.08
     Parks
    -0.08
     проис
    -0.08
     המד
    -0.08
     durchgeführt
    -0.07
     værd
    -0.07
    -0.07
     �
    -0.07
     beslut
    -0.07
    POSITIVE LOGITS
     compliant
    0.08
     endure
    0.08
     entregar
    0.08
     mandated
    0.08
     compliance
    0.08
     соблюдать
    0.08
     complying
    0.08
    严
    0.08
     attaining
    0.08
    YYYY
    0.08
    Act Density 0.020%
    No Known Activations