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

    Neuronpedia

    INDEX
    Explanations

    introducing analogies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     הת
    0.43
     ควร
    0.41
     encompasses
    0.41
    Types
    0.41
     isIn
    0.40
     terdapat
    0.40
     examines
    0.39
     isOn
    0.38
     represents
    0.37
    Impl
    0.37
    POSITIVE LOGITS
    imagine
    0.48
     imagine
    0.46
     это
    0.44
     literalmente
    0.44
     кстати
    0.43
    說是
    0.42
     decirlo
    0.41
     irony
    0.41
     спасибо
    0.40
     זה
    0.40
    Act Density 0.079%

    No Known Activations