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

    Neuronpedia

    INDEX
    Explanations

    unit testing code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Validators
    0.77
    Diagnostics
    0.76
    EXPECT
    0.74
     witchcraft
    0.71
    Accessibility
    0.71
    inos
    0.69
    Acceleration
    0.68
    度的
    0.68
     shouldUse
    0.68
     ),
    0.66
    POSITIVE LOGITS
     freshman
    0.84
    ંકી
    0.83
    蒨
    0.81
    ுங்கள்
    0.81
    িগ্ন
    0.80
    щите
    0.75
     مباشرة
    0.75
    ங்கிணை
    0.74
     ஒன்ற
    0.74
     месту
    0.73
    Act Density 0.000%

    No Known Activations