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

    Neuronpedia

    INDEX
    Explanations

    explaining Gemma or states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ર્થ
    0.49
     đô
    0.46
     শহর
    0.46
    向けの
    0.45
    か
    0.45
    τω
    0.44
    AuthProvider
    0.44
     đất
    0.44
     bạn
    0.43
    व
    0.43
    POSITIVE LOGITS
     complicated
    0.47
     marvellous
    0.47
     самого
    0.47
     permutations
    0.47
     растений
    0.47
     собственно
    0.46
    Вот
    0.45
     elucidation
    0.45
     endlessly
    0.45
     himself
    0.44
    Act Density 0.008%

    No Known Activations