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

    Neuronpedia

    INDEX
    Explanations

    ** formatting elements and associated text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    replacement
    0.50
    দুই
    0.49
    Replacement
    0.47
    unlike
    0.46
     imprim
    0.45
    $/
    0.45
    reshold
    0.44
    Пред
    0.44
     gelas
    0.44
     răz
    0.44
    POSITIVE LOGITS
    도
    0.48
     চলতে
    0.43
     Wr
    0.41
     is
    0.40
    も
    0.40
    ላ
    0.39
    汢
    0.39
    quiries
    0.39
    éticas
    0.39
    herr
    0.39
    Act Density 0.000%

    No Known Activations