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
    (typ
    -0.07
     сучас
    -0.07
    Submit
    -0.06
     Champ
    -0.06
     De
    -0.06
    ह
    -0.06
     Stainless
    -0.06
    Object
    -0.06
    .AddParameter
    -0.06
    User
    -0.06
    POSITIVE LOGITS
    vasive
    0.07
    multi
    0.07
     lä
    0.06
    161
    0.06
    UPI
    0.06
     smash
    0.06
     planners
    0.06
    ตร
    0.06
    .runners
    0.06
    cis
    0.06
    Act Density 0.005%

    No Known Activations