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

    Neuronpedia

    INDEX
    Explanations

    scientific computing and simulations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    holi
    0.45
     modelBuilder
    0.43
    MoodAnalyser
    0.40
     psychosis
    0.39
     lordship
    0.38
    efois
    0.37
     dialogo
    0.37
    だけ
    0.37
     BaseModel
    0.37
    पेक्षा
    0.36
    POSITIVE LOGITS
     Computational
    0.96
     Algorithms
    0.92
    Computational
    0.90
     computational
    0.89
     algorithms
    0.86
    Algorithms
    0.81
     computationally
    0.80
    algorithms
    0.80
    算法
    0.79
     algorith
    0.74
    Act Density 0.004%

    No Known Activations