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

    Neuronpedia

    INDEX
    Explanations

    San Quentin, Caesars, Toluna

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    லாக
    0.41
    貧
    0.40
     poverty
    0.39
    婢
    0.38
    Shard
    0.38
     belongs
    0.38
    穼
    0.38
     crushes
    0.37
     Pigeon
    0.37
     formulated
    0.37
    POSITIVE LOGITS
    änä
    0.47
    ამაშ
    0.46
    machine
    0.43
    alab
    0.39
    definitions
    0.38
    0.38
    ament
    0.38
     coerc
    0.38
    ත්තේ
    0.37
    cz
    0.37
    Act Density 0.001%

    No Known Activations