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

    Neuronpedia

    INDEX
    Explanations

    temperature, physics, large language models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    equalTo
    0.38
    माइंडर
    0.37
     hamil
    0.35
    *}$
    0.35
    োদন
    0.34
    ᖃ
    0.34
    olius
    0.34
     谢
    0.34
     graham
    0.34
    жек
    0.34
    POSITIVE LOGITS
    ,]
    0.36
    Advertisement
    0.35
    ...]
    0.32
     Concent
    0.31
    Agg
    0.31
     Agg
    0.30
    ,
    0.30
     المنا
    0.29
     вмеша
    0.29
    ensitive
    0.29
    Act Density 0.000%

    No Known Activations