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

    Neuronpedia

    INDEX
    Explanations

    internationalization and app features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ceasefire
    0.44
     speculate
    0.43
     fairies
    0.41
     희
    0.38
     relief
    0.38
     speculating
    0.38
    ಖ್ಯ
    0.38
     trading
    0.37
     Relief
    0.37
     wavelengths
    0.37
    POSITIVE LOGITS
    迁移
    0.41
    vercel
    0.38
    PickerDialog
    0.37
    移民
    0.37
     Ketch
    0.37
     মিশ
    0.36
    葡
    0.36
    oko
    0.36
    普
    0.36
    ELIG
    0.36
    Act Density 0.002%

    No Known Activations