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

    Neuronpedia

    INDEX
    Explanations

    4m

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AV
    0.40
     ছেড়ে
    0.38
     misunderstand
    0.38
    0.38
    晉
    0.37
     Western
    0.36
     misunder
    0.36
    anese
    0.36
     얻
    0.36
    身上的
    0.36
    POSITIVE LOGITS
    SetConfig
    0.41
    電
    0.36
    mana
    0.36
    params
    0.35
    গা
    0.35
    alem
    0.35
    apiUrl
    0.34
    deals
    0.34
    param
    0.34
    logos
    0.34
    Act Density 0.001%

    No Known Activations