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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     feast
    -0.07
    (Int
    -0.07
     Dict
    -0.07
    :function
    -0.06
     neb
    -0.06
    _subset
    -0.06
     OST
    -0.06
     pou
    -0.06
    _ghost
    -0.06
    ищ
    -0.06
    POSITIVE LOGITS
    (zone
    0.06
    anny
    0.06
     sorumlu
    0.06
    ledge
    0.06
    <main
    0.06
     medya
    0.06
     disasters
    0.06
     Barney
    0.06
    inidad
    0.05
     Havana
    0.05
    Act Density 0.007%

    No Known Activations