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

    Neuronpedia

    INDEX
    Explanations

    lock or confinement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    న్లు
    0.50
    ȩ
    0.47
    蒈
    0.47
     Übersicht
    0.46
     Kø
    0.46
     Беларуси
    0.46
     Duits
    0.45
    ^{*}=\
    0.44
     Lukas
    0.44
    ₁+
    0.43
    POSITIVE LOGITS
    V
    0.54
    water
    0.50
    M
    0.50
     water
    0.47
    H
    0.47
     and
    0.45
     seclusion
    0.45
    즈
    0.45
     to
    0.45
     confinement
    0.45
    Act Density 0.001%

    No Known Activations