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

    Neuronpedia

    INDEX
    Explanations

    start_of_turn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     uitge
    1.51
     suddiv
    1.49
    鑷
    1.49
    鲷
    1.45
     denaro
    1.42
    จัด
    1.42
    ssä
    1.41
    ặn
    1.39
     biztos
    1.39
    élim
    1.39
    POSITIVE LOGITS
     novoProduto
    1.26
     Berkeley
    1.20
     FB
    1.15
     muscle
    1.14
     jobb
    1.14
     fender
    1.14
    Berkeley
    1.13
     fume
    1.12
     sensor
    1.12
    фт
    1.12
    Act Density 0.006%

    No Known Activations