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

    Neuronpedia

    INDEX
    Explanations

    lists and quantifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     של
    0.44
    Sang
    0.44
    邕
    0.43
    ция
    0.42
     частности
    0.42
    ressant
    0.42
     పాల్
    0.41
    iany
    0.40
     kaçtır
    0.40
    мести
    0.40
    POSITIVE LOGITS
    ’
    0.55
    '
    0.52
    液
    0.51
     operators
    0.50
     tested
    0.49
     relieves
    0.49
     passively
    0.48
     liquids
    0.48
     applications
    0.48
     oxides
    0.47
    Act Density 0.005%

    No Known Activations