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

    Neuronpedia

    INDEX
    Explanations

    I express opinion/sentiment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Remark
    0.53
    ®,
    0.48
     зокрема
    0.48
    Notably
    0.47
    ですが
    0.46
    且
    0.46
     ซึ่ง
    0.46
    (),
    0.45
    、
    0.45
    이며
    0.45
    POSITIVE LOGITS
     nowe
    0.56
     didn
    0.54
     get
    0.53
     exclaimed
    0.52
     these
    0.51
     forgot
    0.50
     These
    0.49
     nieuwe
    0.48
     Jetzt
    0.48
     scared
    0.47
    Act Density 0.060%

    No Known Activations