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

    Neuronpedia

    INDEX
    Explanations

    half-day to full day

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UCK
    0.48
    IDAD
    0.47
    IMS
    0.45
    IL
    0.42
    I
    0.41
    ITH
    0.41
    HO
    0.41
    ARDS
    0.41
    IES
    0.40
    CRUD
    0.40
    POSITIVE LOGITS
     आसानी
    0.52
     მნიშვნელ
    0.49
     campaigning
    0.46
     تن
    0.46
     Manifesto
    0.45
     পাঁচটি
    0.45
     स्थाई
    0.44
     쉽게
    0.44
     लेक्चर
    0.43
     तैनात
    0.43
    Act Density 0.001%

    No Known Activations