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

    Neuronpedia

    INDEX
    Explanations

    #

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    userService
    -0.06
    Predicate
    -0.06
     отправ
    -0.06
    -password
    -0.06
     Saying
    -0.06
    цией
    -0.06
    츠
    -0.06
    rown
    -0.06
    、三
    -0.06
    ве
    -0.06
    POSITIVE LOGITS
     Premiere
    0.06
     bans
    0.06
     이런
    0.06
     cắt
    0.06
    :",↵
    0.06
    ındaki
    0.06
    0.06
     relent
    0.05
    획
    0.05
     orchestr
    0.05
    Act Density 0.003%

    No Known Activations