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

    Neuronpedia

    INDEX
    Explanations

    html head tag

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     líneas
    0.67
     piso
    0.66
     chão
    0.62
     pisos
    0.61
     floor
    0.58
    చ్చి
    0.56
     campo
    0.55
     floors
    0.55
     linhas
    0.54
     góc
    0.54
    POSITIVE LOGITS
    ƣ
    0.80
    赊
    0.78
     সপ্ত
    0.78
     całym
    0.76
    हमारी
    0.75
    স্তন
    0.75
    フェ
    0.75
    퀀
    0.74
    প্রায়
    0.74
     단순히
    0.74
    Act Density 0.020%

    No Known Activations