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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations with 'r'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Fortunately
    0.74
    Suppose
    0.73
    Italia
    0.71
    \,.
    0.69
    Are
    0.68
    Occasionally
    0.66
    ⬤
    0.66
    :])
    0.66
    stereotype
    0.65
    ंच
    0.64
    POSITIVE LOGITS
     enkele
    0.92
     eighteen
    0.85
     parchment
    0.84
     vlak
    0.83
     seventeen
    0.80
     toege
    0.80
     minder
    0.79
     electron
    0.76
     Fighters
    0.76
     uranium
    0.76
    Act Density 0.008%

    No Known Activations