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

    Neuronpedia

    INDEX
    Explanations

    Research papers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    票价
    -0.09
    _Write
    -0.07
     Junction
    -0.07
     approves
    -0.07
     remembered
    -0.07
     blended
    -0.07
     superheroes
    -0.07
    .getCmp
    -0.07
     Yoshi
    -0.06
    masked
    -0.06
    POSITIVE LOGITS
     theory
    0.08
    تظ
    0.07
     פת
    0.07
    的帮助
    0.07
    に向けて
    0.07
     he
    0.06
     וכך
    0.06
    可靠的
    0.06
    層
    0.06
     roy
    0.06
    Act Density 0.009%

    No Known Activations