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

    Neuronpedia

    INDEX
    Explanations

    academic and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hefty
    0.50
     ghost
    0.47
     awkward
    0.47
     having
    0.46
    one
    0.45
     bout
    0.45
     huge
    0.45
     acrobat
    0.44
     stint
    0.44
     soothing
    0.44
    POSITIVE LOGITS
     soorten
    0.63
    ostructures
    0.60
    sciences
    0.57
     prostředí
    0.55
    álie
    0.54
    ūsų
    0.54
    cientes
    0.54
    rivere
    0.54
    ática
    0.54
    entreprise
    0.54
    Act Density 1.169%

    No Known Activations