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

    Neuronpedia

    INDEX
    Explanations

    spring

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     savvy
    -0.07
    훈
    -0.07
     kneeling
    -0.07
    .Angle
    -0.06
     Shuffle
    -0.06
     svo
    -0.06
    ()↵
    -0.06
    اهش
    -0.06
    ")]
↵
    -0.06
    (Math
    -0.06
    POSITIVE LOGITS
    ाइन
    0.07
     militias
    0.07
     cài
    0.07
    澳
    0.06
     boolean
    0.06
    Installed
    0.06
    riages
    0.06
    理解
    0.06
    λιά
    0.06
    ichen
    0.06
    Act Density 0.008%

    No Known Activations