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

    Neuronpedia

    INDEX
    Explanations

    within

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .ms
    -0.08
     bombers
    -0.07
    _Record
    -0.07
    .factory
    -0.07
    官
    -0.07
    بان
    -0.06
     başlayan
    -0.06
    .selected
    -0.06
    materials
    -0.06
    Visible
    -0.06
    POSITIVE LOGITS
     within
    0.07
     during
    0.07
    	to
    0.07
    runner
    0.07
     During
    0.07
     складі
    0.06
    (Debug
    0.06
     dealing
    0.06
     inside
    0.06
    /o
    0.06
    Act Density 0.014%

    No Known Activations