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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bins
    -0.07
    _player
    -0.07
     KING
    -0.07
    creation
    -0.06
    King
    -0.06
    Jer
    -0.06
     peng
    -0.06
     Teresa
    -0.06
     Fak
    -0.06
    iser
    -0.06
    POSITIVE LOGITS
     [.
    0.08
    ):
    0.07
     इसस
    0.07
     ','.
    0.07
    )?.
    0.07
    ])]
    0.07
    ?
    0.07
     OUTER
    0.07
    )?
    0.07
    ें।
    0.07
    Act Density 0.321%

    No Known Activations