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

    Neuronpedia

    INDEX
    Explanations

    Metaverse, offers, appetites

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     보면은
    0.49
    फोर
    0.49
     कटोच
    0.48
    ताच
    0.47
     नकली
    0.46
     Sporting
    0.46
     bestowed
    0.46
     Reactor
    0.45
     देख
    0.44
     reacting
    0.44
    POSITIVE LOGITS
    '\
    0.45
    "
    0.43
     поку
    0.41
    nt
    0.40
    highway
    0.40
    បង្ហាញ
    0.40
    \'
    0.40
    kule
    0.40
    "\
    0.40
    viles
    0.40
    Act Density 0.001%

    No Known Activations