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

    Neuronpedia

    INDEX
    Explanations

    friend, cousin, or character references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ᅱ
    1.16
    ERK
    1.12
    ರ್‌
    1.09
     TeV
    1.07
     DNN
    1.07
     redor
    1.06
    érrez
    1.03
    зыка
    1.03
     учиты
    1.02
     registró
    1.02
    POSITIVE LOGITS
    ts
    0.97
    life
    0.88
    ly
    0.86
    та
    0.85
     Supplements
    0.83
    </strong>
    0.83
    id
    0.82
    ;
    0.80
    .
    0.79
    pos
    0.77
    Act Density 0.001%

    No Known Activations