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

    Neuronpedia

    INDEX
    Explanations

    applied techniques and methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sistema
    0.97
     systèmes
    0.90
     بودن
    0.90
     sistema
    0.90
     système
    0.87
    essere
    0.87
     системе
    0.87
     Systeme
    0.85
     propos
    0.85
     kebijakan
    0.85
    POSITIVE LOGITS
    应用于
    0.95
     applied
    0.95
     performed
    0.91
     conducted
    0.89
    applied
    0.84
     appliquée
    0.84
     aplicado
    0.81
    法
    0.78
     Techniques
    0.75
     Applied
    0.75
    Act Density 0.278%

    No Known Activations