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

    Neuronpedia

    INDEX
    Explanations

    launch all; open the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    search
    0.50
    i
    0.49
    arXiv
    0.45
    e
    0.44
    this
    0.43
    fel
    0.42
     search
    0.42
    they
    0.41
    res
    0.41
    MS
    0.40
    POSITIVE LOGITS
     eko
    0.50
     lunes
    0.49
     Belediye
    0.45
     Munic
    0.45
    骓
    0.45
     jauh
    0.44
     farklı
    0.44
     beerCount
    0.44
    Attk
    0.43
     kaynak
    0.43
    Act Density 0.007%

    No Known Activations