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

    Neuronpedia

    INDEX
    Explanations

    Memorial days and identify cultural

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nitrile
    0.52
     total
    0.51
     nitros
    0.47
     excitation
    0.46
     absolute
    0.46
     protein
    0.45
     huit
    0.45
     penis
    0.44
     absolut
    0.44
     max
    0.44
    POSITIVE LOGITS
    設置
    0.48
    ओं
    0.46
     стаби
    0.44
     সম্ভ
    0.43
    နိုင်ငံ
    0.43
    離婚
    0.43
    思い
    0.42
    有利于
    0.41
    غرب
    0.40
    んと
    0.40
    Act Density 0.003%

    No Known Activations