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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CDC
    -0.06
     фінансов
    -0.06
    １０
    -0.06
    源
    -0.06
    Contains
    -0.06
    _sampling
    -0.06
    _pattern
    -0.06
     Systems
    -0.06
     relies
    -0.06
     timeouts
    -0.06
    POSITIVE LOGITS
    flen
    0.07
     wn
    0.07
     SignUp
    0.07
     uu
    0.06
    фици
    0.06
     uni
    0.06
    ({↵↵
    0.06
     Discrim
    0.06
    атели
    0.06
     onError
    0.06
    Act Density 0.002%

    No Known Activations