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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ในท
    -0.07
     nie
    -0.06
     wz
    -0.06
     manière
    -0.06
    ，即
    -0.06
    ΟΔ
    -0.06
     Eğer
    -0.06
    ,date
    -0.06
    LIMIT
    -0.06
     worthless
    -0.06
    POSITIVE LOGITS
     Course
    0.07
    (vo
    0.06
    -gallery
    0.06
    arious
    0.06
    observeOn
    0.06
    σω
    0.06
    verbs
    0.06
     Vic
    0.06
     Subcommittee
    0.06
     attracting
    0.06
    Act Density 0.004%

    No Known Activations