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

    Neuronpedia

    INDEX
    Explanations

    improvement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    chen
    -0.08
     रू
    -0.08
    che
    -0.08
    vious
    -0.07
     বিভ
    -0.07
    isierung
    -0.07
     terminate
    -0.07
     élevé
    -0.07
     deja
    -0.07
     Examples
    -0.07
    POSITIVE LOGITS
     continually
    0.10
     노력
    0.09
    不断
    0.09
     continuously
    0.09
     Blvd
    0.09
    _found
    0.09
     kontinuier
    0.09
     efforts
    0.08
     contín
    0.08
     initiatives
    0.08
    Act Density 0.013%

    No Known Activations