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

    Neuronpedia

    INDEX
    Explanations

    relative pronouns after punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    0.57
    )
    0.48
    .
    0.43
    "
    0.43
    ."
    0.39
    ]
    0.38
    }
    0.37
    <.
    0.37
    。
    0.37
    ).
    0.36
    POSITIVE LOGITS
     который
    0.75
     которая
    0.75
     जिसमें
    0.71
     jossa
    0.71
    which
    0.67
     which
    0.66
     которое
    0.66
     která
    0.65
     która
    0.63
     ktorá
    0.63
    Act Density 0.016%

    No Known Activations