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

    Neuronpedia

    INDEX
    Explanations

    performance quality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NOT
    0.32
    ALLE
    0.27
    Simple
    0.27
     את
    0.27
     Soyuz
    0.26
    whatever
    0.25
    シンプルな
    0.25
     없는
    0.25
    ほどの
    0.25
    quando
    0.25
    POSITIVE LOGITS
     well
    0.58
     better
    0.54
     differently
    0.50
     beter
    0.50
     poorly
    0.48
     hyvin
    0.47
     lepiej
    0.47
     bolje
    0.46
     tốt
    0.46
     лучше
    0.46
    Act Density 0.071%

    No Known Activations