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

    Neuronpedia

    INDEX
    Explanations

    algebraic concepts and mathematics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Sorry
    0.39
    щото
    0.39
     issues
    0.38
    coffee
    0.38
    ecycle
    0.38
    ewalk
    0.38
     вывод
    0.38
     miles
    0.37
     calories
    0.37
    sorry
    0.37
    POSITIVE LOGITS
     Algebraic
    0.59
     algebraic
    0.56
    algebra
    0.54
     algebra
    0.53
     Veränder
    0.53
     Algebra
    0.52
     algéb
    0.49
     algebraically
    0.48
    Algebra
    0.48
     soluzioni
    0.48
    Act Density 0.026%

    No Known Activations