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

    Neuronpedia

    INDEX
    Explanations

    multilingual text fragments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Recognition
    0.38
    اث
    0.37
    RVCT
    0.36
     Mailing
    0.36
    Brid
    0.36
    луб
    0.36
    ِّ
    0.35
    Zip
    0.35
    لاش
    0.35
    Yield
    0.35
    POSITIVE LOGITS
    これらの
    0.42
    媒
    0.40
     दर्पण
    0.38
    codewords
    0.38
    सरकार
    0.38
     এবারের
    0.38
     сред
    0.37
     கூற
    0.37
     detik
    0.37
    薊
    0.37
    Act Density 0.001%

    No Known Activations