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

    Neuronpedia

    INDEX
    Explanations

    helper

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     —↵↵
    -0.07
    [q
    -0.07
     вул
    -0.07
     سنت
    -0.07
    oord
    -0.07
    33
    -0.06
     involves
    -0.06
    aso
    -0.06
     Cort
    -0.06
     Cz
    -0.06
    POSITIVE LOGITS
    Helper
    0.13
     helper
    0.12
     Helper
    0.11
    helper
    0.10
    _helpers
    0.09
    Helpers
    0.09
     helpers
    0.09
     dbHelper
    0.08
    .helpers
    0.08
    -helper
    0.08
    Act Density 0.003%

    No Known Activations