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

    Neuronpedia

    INDEX
    Explanations

    ium

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Firefox
    -0.07
     LEFT
    -0.07
    ┘
    -0.07
     DON
    -0.07
    .pid
    -0.07
    👧
    -0.07
    PTH
    -0.07
    千万
    -0.07
     USB
    -0.06
     над
    -0.06
    POSITIVE LOGITS
    업
    0.08
     unreal
    0.07
    évén
    0.07
    _seen
    0.07
     verge
    0.07
     waterfront
    0.07
    튄
    0.06
    (alias
    0.06
     semanas
    0.06
    @testable
    0.06
    Act Density 0.001%

    No Known Activations