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

    Neuronpedia

    INDEX
    Explanations

    unfolding processes

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    o
    0.45
    mber
    0.41
    ered
    0.39
    ে
    0.39
    닝
    0.37
     similarly
    0.37
     tư
    0.37
     দায়িত্ব
    0.37
    мб
    0.36
    一样的
    0.36
    POSITIVE LOGITS
    er
    0.55
    gados
    0.41
    erler
    0.40
    ople
    0.38
    ordnet
    0.37
    zas
    0.36
     Lyons
    0.35
    ্সা
    0.35
    लपुर
    0.35
    erade
    0.35
    Act Density 0.001%

    No Known Activations