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

    Neuronpedia

    INDEX
    Explanations

    safety guidelines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    噹
    0.45
     Moreton
    0.44
     Jameson
    0.42
    मध्यप्रदेश
    0.41
     Champ
    0.41
     Hiroshima
    0.41
    िटीज
    0.41
     अर्जुन
    0.40
     کاربر
    0.39
    िफिकेट
    0.39
    POSITIVE LOGITS
    ey
    0.46
    connect
    0.40
    olov
    0.40
    独立
    0.40
    p
    0.39
     Verbind
    0.39
    0
    0.39
    EO
    0.38
    ///
    0.38
    보고
    0.38
    Act Density 30.266%

    No Known Activations