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

    Neuronpedia

    INDEX
    Explanations

    definition and explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     displays
    0.88
     Check
    0.83
     â
    0.77
     Tips
    0.75
     Here
    0.74
     Displays
    0.71
     showcases
    0.70
     Interestingly
    0.70
     сход
    0.69
     check
    0.69
    POSITIVE LOGITS
    umballMachine
    0.92
    Parte
    0.88
    Fundamentals
    0.86
    лить
    0.81
    र्वेद
    0.80
     उसमे
    0.78
     hintergrund
    0.78
    fundamentals
    0.77
    AA
    0.76
     badi
    0.76
    Act Density 0.193%

    No Known Activations