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

    Neuronpedia

    INDEX
    Explanations

    web requests and redirects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    arnos
    0.42
    readystate
    0.39
     myBuilder
    0.39
    <0xB2>
    0.38
     हिस्से
    0.38
    석
    0.38
     сравнению
    0.38
     repeats
    0.37
    삭제
    0.37
    ushi
    0.37
    POSITIVE LOGITS
    Mel
    0.47
    Elder
    0.40
     Elder
    0.40
     Melanie
    0.40
     Portland
    0.39
    ാപ
    0.39
    Held
    0.39
     shaving
    0.39
     debes
    0.38
     ought
    0.38
    Act Density 0.000%

    No Known Activations