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

    Neuronpedia

    INDEX
    Explanations

    hereby granted, attached

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    縊
    0.39
    <unused551>
    0.38
     عادي
    0.37
    fing
    0.37
     विगत
    0.37
    萋
    0.36
    érieur
    0.36
    Gx
    0.36
     অতীতের
    0.36
    गे
    0.36
    POSITIVE LOGITS
     Jas
    0.42
     여기에
    0.40
     here
    0.38
     herein
    0.38
     Pfl
    0.38
     hereby
    0.38
    Jas
    0.38
    ették
    0.37
    ]]),
    0.37
     AM
    0.37
    Act Density 0.002%

    No Known Activations