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

    Neuronpedia

    INDEX
    Explanations

    preposition followed by noun/gerund

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     oczywiście
    0.43
    嚐
    0.38
    ⸜
    0.38
    ото
    0.36
    দোষ
    0.35
     केसांना
    0.35
    destination
    0.35
    それぞれの
    0.35
    ையாள
    0.35
    ','$
    0.35
    POSITIVE LOGITS
     it
    0.53
    它
    0.45
     a
    0.40
    一个小
    0.39
     epistemology
    0.39
     también
    0.38
     dodat
    0.37
     almeno
    0.37
    ’
    0.37
     sogar
    0.37
    Act Density 0.081%

    No Known Activations