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

    Neuronpedia

    INDEX
    Explanations

    Access control keywords

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cincinnati
    -0.07
     transporter
    -0.07
     federation
    -0.07
     Bey
    -0.07
     roast
    -0.07
    BYTES
    -0.07
    Th
    -0.07
    asts
    -0.06
     Coff
    -0.06
     zařízení
    -0.06
    POSITIVE LOGITS
     zelf
    0.07
     rootNode
    0.07
     >>↵↵
    0.07
    .numericUpDown
    0.06
    기는
    0.06
    madı
    0.06
    链接
    0.06
    alf
    0.06
    いや
    0.06
    oine
    0.06
    Act Density 0.004%

    No Known Activations