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

    Neuronpedia

    INDEX
    Explanations

    spectrum of descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wirklich
    0.42
    ងារ
    0.40
     corris
    0.39
    Rug
    0.39
    puri
    0.38
    ?";
    0.38
    ?;
    0.38
     ricon
    0.38
    Sir
    0.37
    ົ້າ
    0.37
    POSITIVE LOGITS
     Ultrasonic
    0.46
     falling
    0.45
    鳴
    0.44
     সিদ্ধ
    0.41
     использование
    0.40
     NAR
    0.40
     Memphis
    0.39
     ABCD
    0.39
    ামের
    0.39
    спользование
    0.39
    Act Density 0.003%

    No Known Activations