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

    Neuronpedia

    INDEX
    Explanations

    experiences the Moon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Storage
    0.43
    lassical
    0.42
    ভিতে
    0.42
    neighbours
    0.41
    ated
    0.40
    observable
    0.40
    name
    0.40
    empty
    0.40
     продаже
    0.39
    ளுக்கு
    0.39
    POSITIVE LOGITS
     mov
    0.44
     shout
    0.40
    authier
    0.38
    怀
    0.38
     decret
    0.38
     positivos
    0.37
     Moved
    0.37
     nesta
    0.37
     shouts
    0.37
     fui
    0.37
    Act Density 0.002%

    No Known Activations