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

    Neuronpedia

    INDEX
    Explanations

    pronouns followed by actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     exceeds
    0.35
     ensures
    0.34
     cục
    0.34
     promotes
    0.33
     受
    0.32
     *
    0.32
     payoff
    0.31
     encompasses
    0.31
     interacts
    0.31
     grooming
    0.31
    POSITIVE LOGITS
     hadn
    0.60
     knew
    0.46
     couldn
    0.42
     remembered
    0.39
    ida
    0.39
     wasn
    0.39
     sabía
    0.39
     soon
    0.39
     explained
    0.37
     laughed
    0.37
    Act Density 0.021%

    No Known Activations