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

    Neuronpedia

    INDEX
    Explanations

    Llama 2

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     సంఘ
    0.45
     영상을
    0.38
    公交
    0.37
    రగ
    0.36
    យៈ
    0.36
    버스
    0.36
     tuned
    0.36
     опять
    0.36
     рисо
    0.36
     Snake
    0.36
    POSITIVE LOGITS
    tourism
    0.46
    گە
    0.37
    forestation
    0.37
    Wen
    0.37
    Simone
    0.36
    Tek
    0.36
    פול
    0.36
     tourism
    0.35
    </b>
    0.35
    kim
    0.34
    Act Density 0.019%

    No Known Activations