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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    roids
    -0.08
     newName
    -0.07
    zv
    -0.07
     위해
    -0.06
    uards
    -0.06
     amusing
    -0.06
    عمل
    -0.06
    診
    -0.06
    redentials
    -0.06
     slick
    -0.06
    POSITIVE LOGITS
     병
    0.07
    _personal
    0.07
    :NO
    0.07
     malt
    0.07
     répond
    0.06
     comprend
    0.06
    (paths
    0.06
     Cambridge
    0.06
     juego
    0.06
    .populate
    0.06
    Act Density 0.000%

    No Known Activations