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

    Neuronpedia

    INDEX
    Explanations

    cold

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _learning
    -0.08
    goto
    -0.08
    .De
    -0.08
     Learning
    -0.07
     voluptatem
    -0.07
     പരീക്ഷ
    -0.07
    gone
    -0.07
    RT
    -0.07
    .Switch
    -0.07
    Exam
    -0.07
    POSITIVE LOGITS
     genug
    0.10
     ترین
    0.09
    তম
    0.09
     جدًا
    0.08
    Enough
    0.08
     inspirations
    0.08
     genoeg
    0.08
     surround
    0.08
     zones
    0.08
     جداً
    0.08
    Act Density 0.013%

    No Known Activations