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

    Neuronpedia

    INDEX
    Explanations

    widespread destruction, mocking your

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     learned
    0.48
     diverso
    0.46
    i
    0.44
     ponte
    0.44
    AW
    0.42
     Interests
    0.42
     Coleman
    0.42
     Learned
    0.42
     approach
    0.41
     diversa
    0.40
    POSITIVE LOGITS
    Yoga
    0.45
    ز
    0.43
     मसलन
    0.42
    搭载
    0.42
    дох
    0.42
    SDL
    0.41
    }}"
    0.41
     ₹
    0.40
    십
    0.40
    lapse
    0.40
    Act Density 0.002%

    No Known Activations