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

    Neuronpedia

    INDEX
    Explanations

    tensorflow keras imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     extending
    0.38
    䄱
    0.38
    阠
    0.37
    უს
    0.37
    㖘
    0.36
    䀼
    0.36
     मज
    0.35
     केलेल्या
    0.35
     दिल्‍ली
    0.35
    伡
    0.35
    POSITIVE LOGITS
    \},\{
    0.40
    gast
    0.40
    ophyll
    0.40
    Lin
    0.39
    --',
    0.39
     газа
    0.38
     sonde
    0.37
     هيك
    0.36
     OPEC
    0.36
    鲵
    0.36
    Act Density 0.000%

    No Known Activations