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

    Neuronpedia

    INDEX
    Explanations

    subtle or mild

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     굉장히
    0.50
     மட்டுமல்ல
    0.47
     tratamiento
    0.47
     هذه
    0.45
     மட்டுமே
    0.45
    otional
    0.45
     exhort
    0.44
     بهذه
    0.44
    ting
    0.42
     Brito
    0.42
    POSITIVE LOGITS
     seaf
    0.41
    能
    0.40
    Camera
    0.39
    ωση
    0.39
    ূ
    0.39
    ("
    0.38
    Rom
    0.38
    ექ
    0.38
     vinter
    0.38
    琹
    0.38
    Act Density 0.011%

    No Known Activations