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
    Notably
    1.11
    较为
    1.08
    にて
    1.00
     Notably
    0.98
     এরূপ
    0.97
     poiché
    0.95
     نیز
    0.93
     oldukça
    0.92
     hehe
    0.91
    較
    0.89
    POSITIVE LOGITS
     throw
    0.90
     sitting
    0.88
     wanna
    0.87
     look
    0.85
     throws
    0.84
    াম্প
    0.81
     sit
    0.81
     surround
    0.78
     sat
    0.77
     threw
    0.76
    Act Density 0.078%

    No Known Activations