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

    Neuronpedia

    INDEX
    Explanations

    bracket symbol

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    974
    -0.06
     metrics
    -0.06
    David
    -0.06
    resas
    -0.06
    oded
    -0.06
    columns
    -0.06
    ｱ
    -0.06
    data
    -0.06
    μένα
    -0.06
    richText
    -0.06
    POSITIVE LOGITS
    -get
    0.07
    Kick
    0.07
     eslint
    0.07
    urve
    0.07
     eman
    0.07
     や
    0.07
     retard
    0.06
    Tôi
    0.06
     krás
    0.06
     showcased
    0.06
    Act Density 0.001%

    No Known Activations