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

    Neuronpedia

    INDEX
    Explanations

    RESTful APIs, Sci-Fi genres

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    די
    0.68
    璇
    0.65
     retrieve
    0.64
    識
    0.63
     Robson
    0.59
     देवगन
    0.59
     McIl
    0.59
     turbine
    0.58
     фами
    0.57
    ocon
    0.57
    POSITIVE LOGITS
    zieć
    0.76
    Bern
    0.70
     Bern
    0.70
     nies
    0.69
     यार
    0.69
     ++
    0.67
     Newell
    0.67
     चाहता
    0.67
    ellow
    0.66
    urther
    0.65
    Act Density 0.099%

    No Known Activations