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

    Neuronpedia

    INDEX
    Explanations

    accommodation, hostel, hiring

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Requirements
    0.46
    MAK
    0.39
    pJ
    0.39
     esforços
    0.39
    Requirements
    0.39
     tương
    0.38
     unite
    0.37
     digested
    0.36
    AlignCenter
    0.36
    alım
    0.36
    POSITIVE LOGITS
     snakes
    0.42
    accompan
    0.39
    snake
    0.39
    bay
    0.38
     implying
    0.37
    駆け
    0.37
    modation
    0.37
    னமாக
    0.36
    원본파일명
    0.36
    innov
    0.36
    Act Density 0.003%

    No Known Activations