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

    Neuronpedia

    INDEX
    Explanations

    justifications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	lines
    -0.06
     испыт
    -0.06
    人们
    -0.06
    .failed
    -0.06
     bbc
    -0.06
     stepping
    -0.06
     minister
    -0.06
     isbn
    -0.06
     وع
    -0.06
     accountant
    -0.06
    POSITIVE LOGITS
     karar
    0.08
     gag
    0.06
     extents
    0.06
    ↵↵↵↵↵↵
    0.06
    (formData
    0.06
     nécessaire
    0.06
    umm
    0.06
    (attrs
    0.06
    _SETUP
    0.06
    _UI
    0.06
    Act Density 0.023%

    No Known Activations