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

    Neuronpedia

    INDEX
    Explanations

    disclaimers and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    vi
    0.45
    ള
    0.45
    sti
    0.44
     monaster
    0.44
    주고
    0.44
     id
    0.43
     prev
    0.43
    Prob
    0.42
    Allocator
    0.42
    र्ने
    0.42
    POSITIVE LOGITS
    ayangkan
    0.50
     terrifying
    0.49
     frightening
    0.47
     demons
    0.47
    <unused346>
    0.47
     Pokémon
    0.46
    é
    0.46
    ností
    0.46
    రకు
    0.46
    👮
    0.46
    Act Density 0.000%

    No Known Activations