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

    Neuronpedia

    INDEX
    Explanations

    . followed by "It" or "To"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    {
    1.05
     CLE
    0.92
     femoral
    0.92
     gasp
    0.92
    }
    0.90
     Suez
    0.87
    1
    0.87
    ))
    0.86
     precepts
    0.86
     moiety
    0.86
    POSITIVE LOGITS
    ā
    1.28
    ере
    1.12
    am
    1.11
    adari
    1.06
    akit
    1.05
    ara
    1.04
    ор
    1.02
    کش
    1.02
    ak
    1.02
    ारा
    1.01
    Act Density 0.072%

    No Known Activations