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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    phony
    -0.07
    ix
    -0.07
    𝜃
    -0.07
     فأ
    -0.07
    sumer
    -0.07
     сам
    -0.07
     regression
    -0.07
    捕
    -0.07
    .ToLower
    -0.07
    했
    -0.07
    POSITIVE LOGITS
    党史学习
    0.08
    耕耘
    0.08
     ремонт
    0.07
    门槛
    0.07
    ꪕ
    0.07
     günlük
    0.06
    Ｅ
    0.06
    Haunted
    0.06
    -cent
    0.06
     mücadele
    0.06
    Act Density 0.016%

    No Known Activations