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

    Neuronpedia

    INDEX
    Explanations

    Lithium

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aloud
    -0.09
    stukken
    -0.09
     mistake
    -0.08
     ლ
    -0.08
     regularmente
    -0.08
     redirect
    -0.08
     deduct
    -0.07
     manually
    -0.07
    cional
    -0.07
    umik
    -0.07
    POSITIVE LOGITS
     sodium
    0.09
     коммер
    0.09
     выбран
    0.08
    فس
    0.08
     технологий
    0.08
     phosph
    0.08
     citrate
    0.08
     максимально
    0.08
     Sodium
    0.08
     драй
    0.08
    Act Density 0.002%

    No Known Activations