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

    Neuronpedia

    INDEX
    Explanations

    JavaScript code syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     even
    -1.59
    ),
    -1.30
     this
    -1.30
    ).
    -1.16
    )
    -1.13
     almost
    -1.09
     on
    -1.06
     навіть
    -1.05
    .)
    -1.04
     for
    -0.98
    POSITIVE LOGITS
     {};
    1.42
    »;
    1.35
     "";
    1.27
    }$;
    1.24
     '';
    1.24
    {};
    1.21
    ”;
    1.20
    '';
    1.18
     indes
    1.16
    ();
    1.14
    Act Density 0.006%

    No Known Activations