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

    Neuronpedia

    INDEX
    Explanations

    unspecified or unidentified details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     любой
    0.54
     любую
    0.47
     Stupid
    0.46
     उतना
    0.42
     योग्य
    0.41
    redos
    0.41
     যতদিন
    0.41
    िक्त
    0.40
     ততক্ষণ
    0.40
    任何
    0.40
    POSITIVE LOGITS
     unidentified
    1.63
     presumably
    1.59
     unspecified
    1.49
     apparent
    1.41
     apparently
    1.40
     Presumably
    1.35
     unnamed
    1.33
     offenbar
    1.32
    presumably
    1.31
     unknown
    1.27
    Act Density 0.063%

    No Known Activations