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

    Neuronpedia

    INDEX
    Explanations

    what kind of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     translation
    0.44
     fascin
    0.43
     तालुक्यातील
    0.40
     willow
    0.39
    चारी
    0.39
    čar
    0.38
     teapot
    0.38
     ثلاثه
    0.37
    chino
    0.37
    蔽
    0.37
    POSITIVE LOGITS
    𝐊
    0.53
    efois
    0.52
    ন্দ্ব
    0.50
     IVA
    0.50
     Soul
    0.49
     conhecido
    0.49
     métall
    0.48
    ів
    0.48
     অধর
    0.48
    ού
    0.48
    Act Density 0.002%

    No Known Activations