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

    Neuronpedia

    INDEX
    Explanations

    `do` block start

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Daw
    0.50
    することも
    0.38
    assie
    0.37
     adoptar
    0.37
    证实
    0.37
    woods
    0.36
    الش
    0.36
    ूव
    0.36
    0.36
     indica
    0.36
    POSITIVE LOGITS
     {
    0.47
     //!
    0.43
    בודה
    0.43
    Until
    0.41
     //{
    0.39
    Till
    0.39
     {}
    0.38
    τικού
    0.38
     {}\
    0.38
    Tinh
    0.38
    Act Density 0.003%

    No Known Activations