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

    Neuronpedia

    INDEX
    Explanations

    analytical concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     previo
    0.45
    트는
    0.45
    んですよね
    0.45
    もしくは
    0.44
     ಕಾರಣ
    0.43
     לא
    0.43
     способность
    0.42
    κ
    0.42
    uo
    0.41
     얘는
    0.41
    POSITIVE LOGITS
     analytic
    0.48
     analyze
    0.46
     Analyze
    0.45
     analyzing
    0.44
     Analyzing
    0.43
    ]
    0.41
     analisis
    0.41
     Conducting
    0.41
     analyzer
    0.41
     Analytical
    0.41
    Act Density 0.023%

    No Known Activations