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

    Neuronpedia

    INDEX
    Explanations

    deep down

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     diffère
    0.62
     apostila
    0.62
     dlg
    0.62
    م
    0.62
    طا
    0.61
     Ländern
    0.57
     terraz
    0.55
     pagina
    0.55
    وير
    0.55
    عيد
    0.55
    POSITIVE LOGITS
    ности
    0.61
    structural
    0.59
    ylated
    0.57
    сий
    0.57
    an
    0.56
    ability
    0.55
    plicity
    0.53
     ample
    0.52
    ocyte
    0.50
    stereotype
    0.50
    Act Density 0.001%

    No Known Activations