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

    Neuronpedia

    INDEX
    Explanations

    prepositions and formal language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	Response
    -0.08
    abling
    -0.08
    enuity
    -0.07
    -op
    -0.07
    YPE
    -0.07
     dop
    -0.07
    _Enable
    -0.07
    .level
    -0.07
    APPLE
    -0.07
     Panc
    -0.06
    POSITIVE LOGITS
     сна
    0.07
    ��
    0.06
    Master
    0.06
    稿
    0.06
    signed
    0.06
    ([
↵
    0.06
     elves
    0.06
    ']
↵
    0.06
    ']*
    0.05
     listOf
    0.05
    Act Density 0.139%

    No Known Activations