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

    Neuronpedia

    INDEX
    Explanations

    Advice, cautions, or personal experiences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    无需
    -0.09
     unrelated
    -0.08
    CE
    -0.08
    如下
    -0.08
    (def
    -0.08
    ю
    -0.07
    анда
    -0.07
    열
    -0.07
     crude
    -0.07
    只能
    -0.07
    POSITIVE LOGITS
     adequately
    0.12
     properly
    0.12
     correctement
    0.11
     suficientemente
    0.11
     पर्याप्त
    0.10
     suficientes
    0.10
     timely
    0.10
     siquiera
    0.10
     genug
    0.10
     ausreich
    0.10
    Act Density 0.305%

    No Known Activations