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

    Neuronpedia

    INDEX
    Explanations

    code and structured data explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    য়াদ
    0.84
     quod
    0.82
    <unused1918>
    0.81
    द्दल
    0.79
    ୁ
    0.78
     previsto
    0.78
     blunt
    0.76
     Blizzard
    0.75
     prohib
    0.74
     rapid
    0.74
    POSITIVE LOGITS
    "/>
    0.88
    """
    0.83
    等等
    0.80
    }
    0.79
     }
    0.76
     }}
    0.76
    <h2>
    0.75
    </div>
    0.74
    </li>
    0.74
     }}}
    0.73
    Act Density 0.417%

    No Known Activations