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

    Neuronpedia

    INDEX
    Explanations

    html closing tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hordes
    0.36
    𒐪
    0.34
     meningkat
    0.33
     outrageous
    0.33
     самого
    0.33
    твор
    0.31
     outlandish
    0.31
    Silicon
    0.31
     훨씬
    0.31
     OSHA
    0.31
    POSITIVE LOGITS
     Also
    0.50
    </li>
    0.49
    </h2>
    0.49
    </h3>
    0.47
    </h1>
    0.43
    */
    0.42
     Note
    0.41
    </span>
    0.40
     Please
    0.40
     Including
    0.40
    Act Density 8.446%

    No Known Activations