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

    Neuronpedia

    INDEX
    Explanations

    logical deduction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    xspace
    0.42
     financiar
    0.42
    IEEE
    0.41
     calculado
    0.39
    crollView
    0.39
    utente
    0.39
    kowicz
    0.38
    CSV
    0.38
    iau
    0.38
    ਾਈ
    0.37
    POSITIVE LOGITS
     logical
    0.73
     Logical
    0.70
     logic
    0.68
    逻辑
    0.67
     Logic
    0.65
     deductive
    0.64
    推理
    0.63
     logically
    0.63
     syll
    0.61
     transitive
    0.59
    Act Density 0.039%

    No Known Activations