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

    Neuronpedia

    INDEX
    Explanations

    modal verbs and intensifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SOS
    0.88
    Simulation
    0.86
    Diabetes
    0.80
    SIM
    0.79
    DL
    0.78
    Diagram
    0.76
    Symptoms
    0.76
    DNA
    0.76
    Pract
    0.76
    Dollar
    0.76
    POSITIVE LOGITS
    picode
    0.82
     суме
    0.81
    педия
    0.77
     undergrad
    0.76
    ал
    0.76
    uintes
    0.76
    commonByteArray
    0.76
    ки
    0.75
    ги
    0.75
     জন্
    0.74
    Act Density 0.124%

    No Known Activations