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

    Neuronpedia

    INDEX
    Explanations

    HTML/XML closing tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ():
    0.92
     '-':
    0.86
    alors
    0.85
     seguintes
    0.83
    `:
    0.82
     seguinte
    0.82
    "):
    0.80
     calor
    0.79
    +:
    0.79
    **:
    0.79
    POSITIVE LOGITS
     />
    1.74
    />
    1.55
    /><
    1.40
     /><
    1.36
     />;
    1.30
     /></
    1.21
     />);
    1.19
     />,
    1.18
     />';
    1.15
     ></
    1.09
    Act Density 0.076%

    No Known Activations