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

    Neuronpedia

    INDEX
    Explanations

    Unreal Engine and stride

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rijke
    1.04
    ்
    1.03
     след
    0.95
     gadgets
    0.93
    பு
    0.92
    릿
    0.92
    𝑟
    0.91
    hydration
    0.91
    ர்
    0.89
    loride
    0.88
    POSITIVE LOGITS
     depth
    0.91
     awhile
    0.89
     gostaria
    0.86
     चाहता
    0.85
    はその
    0.84
    depth
    0.84
    ยนต์
    0.83
     director
    0.83
    是因为
    0.83
    {~
    0.82
    Act Density 0.003%

    No Known Activations