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

    Neuronpedia

    INDEX
    Explanations

    structured options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     stdin
    0.72
     motivations
    0.71
     inox
    0.71
     IconButton
    0.71
     instincts
    0.70
     inefficiencies
    0.70
     ulcers
    0.69
     slowdown
    0.69
    odnik
    0.69
     ఉ
    0.68
    POSITIVE LOGITS
    Western
    0.72
    US
    0.71
    us
    0.71
    western
    0.70
     dahil
    0.69
    ast
    0.66
    较高
    0.66
     बढ़िया
    0.66
    ละ
    0.66
     Western
    0.65
    Act Density 0.082%

    No Known Activations