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

    Neuronpedia

    INDEX
    Explanations

    offering elaboration on aspects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     copious
    0.67
     abundante
    0.65
     allerlei
    0.63
     যাবত
    0.61
    果然
    0.60
     abundant
    0.60
     بسیار
    0.60
    major
    0.60
     যাবতীয়
    0.59
    各类
    0.58
    POSITIVE LOGITS
     studying
    1.05
     analysing
    0.98
     designing
    0.92
     analyzing
    0.91
     making
    0.90
     discussing
    0.89
     configuring
    0.85
     owning
    0.84
     explaining
    0.83
     Designing
    0.83
    Act Density 0.160%

    No Known Activations