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

    Neuronpedia

    INDEX
    Explanations

    be able to be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ة
    1.69
     byli
    1.30
    ري
    1.23
     imprescind
    1.21
    nicht
    1.20
     keine
    1.16
    not
    1.15
     कमजोरी
    1.15
    ls
    1.14
    мы
    1.14
    POSITIVE LOGITS
     able
    1.12
    ко
    1.10
     part
    1.06
     modernized
    1.02
     customer
    1.01
     phép
    1.01
     newly
    0.98
     grateful
    0.98
    있
    0.98
     generous
    0.98
    Act Density 0.142%

    No Known Activations