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

    Neuronpedia

    INDEX
    Explanations

    stating or arguing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Thanks
    0.43
    ですので
    0.43
     Thanks
    0.40
     gespeichert
    0.40
     thanks
    0.39
    ܣ
    0.39
    )));
    0.39
    {}{
    0.38
    ించాలి
    0.38
    Наи
    0.38
    POSITIVE LOGITS
     saying
    1.60
     citing
    1.54
     stating
    1.52
     noting
    1.49
     arguing
    1.34
     diciendo
    1.29
     dizendo
    1.29
     claiming
    1.27
     Noting
    1.25
    citing
    1.23
    Act Density 0.022%

    No Known Activations