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

    Neuronpedia

    INDEX
    Explanations

    just not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Flipper
    0.39
     করলাম
    0.38
     নিঃস
    0.38
    ູບ
    0.38
     করিম
    0.37
    хов
    0.37
    Applying
    0.37
    Caching
    0.37
     সড়
    0.36
     시설
    0.36
    POSITIVE LOGITS
     sometime
    0.42
     resigned
    0.41
     notoriously
    0.41
     held
    0.40
     disagree
    0.40
     celebrated
    0.40
     joined
    0.39
     humiliated
    0.39
     fielded
    0.39
     nonuniform
    0.38
    Act Density 0.001%

    No Known Activations