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

    Neuronpedia

    INDEX
    Explanations

    specific aspect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     exactamente
    0.93
     exatamente
    0.91
     Exactly
    0.89
     exacte
    0.87
     esattamente
    0.86
     exact
    0.85
     exactly
    0.85
    exactly
    0.83
     بالضبط
    0.81
     Exact
    0.81
    POSITIVE LOGITS
     aspect
    1.76
    aspect
    1.61
     aspects
    1.58
     particular
    1.46
     Aspect
    1.37
    Aspect
    1.36
     aspecto
    1.33
     aspectos
    1.32
     aspetti
    1.30
     aspekt
    1.30
    Act Density 0.119%

    No Known Activations