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

    Neuronpedia

    INDEX
    Explanations

    existence, remnants

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Stream
    -0.08
    652
    -0.07
    _annotation
    -0.07
    ID
    -0.06
    “To
    -0.06
    Path
    -0.06
     Alabama
    -0.06
    今
    -0.06
    “That
    -0.06
     Loading
    -0.06
    POSITIVE LOGITS
    lder
    0.07
    _WHITE
    0.07
    (Border
    0.06
     kont
    0.06
    =$
    0.06
    ßen
    0.06
    ervers
    0.06
     نیروی
    0.06
     bieten
    0.06
    ByVersion
    0.06
    Act Density 0.024%

    No Known Activations