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

    Neuronpedia

    INDEX
    Explanations

    This significantly access

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ps
    0.49
    cross
    0.47
    cement
    0.46
    citations
    0.45
    ben
    0.45
    bach
    0.45
    empat
    0.43
    cja
    0.43
    gens
    0.43
    cents
    0.43
    POSITIVE LOGITS
    വിലെ
    0.53
     कल्याण
    0.40
     создание
    0.40
     देशभ
    0.39
    㫣
    0.39
     സമ്പ
    0.39
     হই
    0.39
     नीति
    0.38
     creado
    0.38
    ைத்
    0.38
    Act Density 0.003%

    No Known Activations