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

    Neuronpedia

    INDEX
    Explanations

    digits and numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     retirees
    -0.08
     hypert
    -0.08
     бүр
    -0.08
     अच्छी
    -0.08
    वाह
    -0.08
    istung
    -0.08
     paligid
    -0.08
    เครื่อง
    -0.08
    “五
    -0.08
    “三
    -0.08
    POSITIVE LOGITS
     два
    0.10
     দুটি
    0.10
     fudge
    0.09
     બે
    0.09
     দু
    0.08
    两个
    0.08
     two
    0.08
    two
    0.08
    nd
    0.08
     两
    0.08
    Act Density 0.057%

    No Known Activations