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

    Neuronpedia

    INDEX
    Explanations

    pronouns followed by verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    डो
    0.46
     definitely
    0.43
     Definitely
    0.43
     Awesome
    0.42
     रिंग
    0.42
     awesome
    0.42
     galera
    0.40
     rallying
    0.40
     cooldown
    0.39
     pivoting
    0.39
    POSITIVE LOGITS
     increasingly
    0.46
    ronic
    0.45
     marvel
    0.45
     sought
    0.44
     dares
    0.43
     seldom
    0.42
    越来越多
    0.42
     experiment
    0.41
     dared
    0.40
     Increasingly
    0.40
    Act Density 0.004%

    No Known Activations