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

    Neuronpedia

    INDEX
    Explanations

    the three button 3

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Surname
    0.46
    ίζουν
    0.46
    ర్
    0.46
     শ্রীমতি
    0.45
    Ễ
    0.44
    ધ્ય
    0.43
    ﺨ
    0.43
    ρια
    0.43
    ディー
    0.42
    ίος
    0.42
    POSITIVE LOGITS
     .
    0.50
     Fasc
    0.47
     seperate
    0.46
     jus
    0.45
     which
    0.43
     fascinating
    0.43
    zoom
    0.43
     Origins
    0.43
     trans
    0.42
     isolated
    0.42
    Act Density 0.043%

    No Known Activations